人工知能学会論文誌
検索
OR
閲覧
検索
30 巻 , 1 号
一般論文/特集論文「Webインテリジェンスとインタラクションの新展開」,「オノマトペの利活用」,「近未来チャレンジ2013」
選択された号の論文の38件中1~38を表示しています
    • |<
    • <
    • 1
    • >
    • >|
一般論文
原著論文
  • 山内 翔, 川村 秀憲, 鈴木 恵二
    30 巻 (2015) 1 号 p. 1-11
    公開日: 2015/01/06
    ジャーナル フリー
    The main feature that keeps states and structures stable can be seen in living organisms. This adjusting and adaptive feature is called homeostasis. This integrated adaptive feature is achieved by the cooperation of organs in living organisms. Living organisms in nature act dynamically due to this feature. Highly adaptive behavior caused by this feature is also observed in simple living organisms that have no neural circuits such as amoebas. In amoeba case, each cell acts as an oscillator and such behavior is explicable as synchronization phenomena of oscillators. Based on these facts, a method of control to generate homeostasis in robotic systems is proposed by assuming a robot system is an aggregation of oscillators in this paper. When a robot system is assumed as an aggregation of oscillators, a robot system tries to keep the value of the specific function that indicate its uncomfortable level small the whole time. To keep such function value small, a robot system stabilize the relationship between oscillators when its value is small and reconstruct the relationship between oscillators when its value is large. This behavior is also explicable as synchronization phenomena of oscillators. A redundant robot arm is made to confirm the effect of this control method to generate homeostatic behaviors in robotic systems.
    抄録全体を表示
  • 小野 博紀, 内海 彰
    30 巻 (2015) 1 号 p. 12-21
    公開日: 2015/01/06
    ジャーナル フリー
    Causal knowledge is important for decision-making and risk aversion. However, it takes much time and effort to extract causal knowledge manually from a large-scale corpus. Therefore, many studies have proposed several methods for automatically extracting causal knowledge. These methods use a variety of linguistic or textual cues indicating causality on the basis of the assumption that causally related events tend to co-occur within a document. However, because of this assumption, they cannot extract causal knowledge that is not explicitly described in a document. Therefore, in this paper, we propose a novel method for extracting causal knowledge not explicitly described in a document using time series analysis of events. In our method, event expressions, which are represented by a pair of a noun phrase and a verb phrase, are extracted from newspaper articles. These extracted event expressions are clustered into distinct events, and the burst of the appearance of these clustered events is detected. Finally, using the time series data with burst, it is judged whether any event pairs have a causal relationship by Granger Causality test. We demonstrate through an evaluation experiment that the proposed method successfully extracts valid causal knowledge, almost all of which cannot be extracted by existing cue-based methods.
    抄録全体を表示
  • 西村 悟史, 笹嶋 宗彦, 來村 徳信, 中村 明美, 高橋 弘枝, 平尾 明美, 服部 兼敏, 溝口 理一郎
    30 巻 (2015) 1 号 p. 22-36
    公開日: 2015/01/06
    ジャーナル フリー
    Nurses' daily practices are performed according to nursing guidelines of hospitals. Novice nurses learn by consulting the bulky files of the guidelines for their practices. The nurses' actions in practice are usually transmitted from experienced nurses to the novices through the daily practices. It is difficult to represent complex and intertwined actions with their goals by the paper guidelines. The goal of the actions is often implicit knowledge accumulated through the nurses' daily practices. To cope with this problem, we have previously proposed a goal realization model called ``CHARM'' (an abbreviation for ``Convincing Human Action Rationalized Model''). Unlike in the printed guidelines, CHARM can represent the goal of actions. We have described nursing actions and their goals as CHARM trees constructed from real nursing guidelines used in a hospital through consultation with experienced nurses. On the other hand, the novices need to learn sequence of the actions. Therefore we developed a tablet computer, which is called CHARM Pad, for browsing CHARM trees with two modes corresponding to the both viewpoints. The novices are able to learn nursing actions with their goals by both goal-oriented viewpoint and sequence-oriented viewpoint. The CHARM Pad has been used for training of the novice nurses at ICU unit. After the training, we received positive comments from the chief nurse in the ICU unit and the chief nurse in the Nursing Department. Questionnaires completed by the novice nurses also showed that the two modes of the CHARM Pad helped them to understand the goals and the sequence of the actions.
    抄録全体を表示
  • 小川 泰右, 池田 満, 鈴木 斎王, 荒木 賢二
    30 巻 (2015) 1 号 p. 37-46
    公開日: 2015/01/06
    ジャーナル フリー
    PROBLEM is a key concept used in sharing intentions of medical services among health professionals belonging to different domains. PROBLEMs represent the necessity for medical services from each domain. PROBLEMs serve as a reference point for unifying multiple domain knowledge, when health professional team designs services. However, there is confusion on sharing intentions of the medical services using PROBLEMs. The confusion arose from the ambiguity of the role which the PROBLEMs are playing on intention expressions. Hence, the authors developed a media equipped with a function which specifies roles of PROBLEMs, and tried to control of this confusion. The result of the trial use suggests that the media suppresses the confusion and prompts users to externalize intentions of medical services.
    抄録全体を表示
  • 村松 慶一, 戸川 達男, 小島 一晃, 松居 辰則
    30 巻 (2015) 1 号 p. 47-60
    公開日: 2015/01/06
    ジャーナル フリー
    The color research has much interest in exploring emotional responses to color stimuli, which are referred to as color emotions. In general, color emotions are measured through psychological methods and represented as values on rating scales. For further understanding of color emotions and development of their effective application, conceptual structure of color emotions and rating scales need to be shared among various disciplinary fields. One typical approach in sharing such knowledge is to clarify concepts as an ontology. In this paper, we specified color emotions based on psychological attributes and built an ontology with an ontology development environment Hozo and a top-level ontology YAMATO. As a result, our ontology describes 16 psychological attributes which are measured by rating scales on the basis of a concept of human awareness. Approximately 74.7 percent of instances of the psychological attributes, which are frequently used in articles on measurement of color emotions, are accounted by the 16 psychological attributes. By adding descriptions of psychological attributes which are infrequently used and have not been fully elucidate in the color research, our ontology would increase utility for knowledge sharing and be feasible in prompting scientific and engineered approaches to understand human mind.
    抄録全体を表示
論文特集「Webインテリジェンスとインタラクションの新展開」
原著論文
  • 竹腰 大輔, 荒木 雅弘
    30 巻 (2015) 1 号 p. 61-70
    公開日: 2015/01/06
    ジャーナル フリー
    With the spread of mobile devices, need for development methodology of MMI (MultiModal Interaction) systems is increasing in recent years. We have designed a new object-oriented MMI description language named MrailsScript which is based on the data model definition. MrailsScript has maintainability and scalability compared with previous languages which based on the finite state model. The data model definition is based on semantic web ontology that makes the definition process simpler and can use meta-data of Linked Open Data. However the developer is required to learn about related semantic web technologies in order to take advantage of MrailsScript. The aim of this research is to develop a new Multimodal interactive system development environment, named MrailsBuilder, which is based on ontological knowledge. MrailsBuilder supports data model definition process by visualizing the structure of ontology. In addition, MrailsBuilder automatically generates SPARQL query from MrailsScript which creates the target contents of the MMI system from Linked Open Data with the inference capability. We developed an example MMI systems using this MrailsBuilder and examined its facilities of development process.
    抄録全体を表示
  • 井口 晃一, 土方 嘉徳, 西田 正吾
    30 巻 (2015) 1 号 p. 71-83
    公開日: 2015/01/06
    ジャーナル フリー
    Recommendation service is becoming popular in many e-commerce sites and content distribution sites (e.g. news, movies and games). In this service, the system identifies an individual by a login certification and extracts information about interest and preference from the user. It finally recommends items that a user seems to be interested in based on the information. However, a recommendation function is not popular in a TV set (recommending TV programs) whereas it is widely used in the Web-based services. The most crucial reason is that it is difficult to identify an individual sitting in front of the TV, which are usually shared by several members of the family. These users usually do not want to perform additional operation on the remote control for login authentication. This means that it is not possible to make a user profile about the personal interest and preference. Therefore, in this study, we propose a technique to individualize a user profile from the viewing log mixed with several users.
    抄録全体を表示
  • Sorn Jarukasemratana, Tsuyoshi Murata
    30 巻 (2015) 1 号 p. 84-95
    公開日: 2015/01/06
    ジャーナル フリー
    In this paper, we propose a two-step algorithm to perform a community detection in scale-free networks. One of the main characteristics of scale-free networks is that node degree distribution follows a power law. However, during our own experiments, we encountered another sub-type of scale-free networks which we call ``mixed scale-free networks". Some communities have hub nodes and node degree follows power law distribution, while some communities do not have hub nodes and node degree follows normal distribution. For mixed scale-free networks, methods that do not specifically design for scale-free will have difficulties because of the scale-free properties. At the same time, scale-free based methods will have difficulties because some communities have node degree follows normal distribution. In this research, we propose a community detection algorithm that can work on networks that contain both types of communities at the same time. Our method can handle this case correctly because our algorithm performs both scale-free and non scale-free approaches iteratively. To evaluate our method, we use NMI - Normalized Mutual Information - to measure our results on both synthetic and real-world datasets comparing with both scale-free and non scale-free community detection methods. The results show that, our method outperforms baseline methods on mixed scale-free networks and scale-free networks while performs equally on networks with normal degree distribution.
    抄録全体を表示
  • 仲田 圭佑, 村田 剛志
    30 巻 (2015) 1 号 p. 96-101
    公開日: 2015/01/06
    ジャーナル フリー
    Recent development of information technology and rise of social media enable us to access massive data. Large scale data such as hyperlink structure in WWW and friendship information in social media can be represented as networks based on graph theory. For analyzing such data, many methods have been proposed. Among them, the methods called community detection have advantages that they can make networks simple and easy to understand. However, most of them had not considered the background knowledge of data, thus some methods called constrained community detection which take such background knowledge into consideration have been proposed. Constrained community detection methods show robust performance on noisy data due to its background knowledge. In particular, constrained Hamiltonian-based community detection methods have advantages such as flexibility of output results. The Hamiltonian, energy in statistical mechanics, can be theoretically considered as a generalization of the Newman's modularity. In this paper, we propose a method for accelerating constrained community detection based on Hamiltonian. Our proposed method is a variant of Blondel's Louvain method which is known for its computational efficiency. We experimentally show that the proposed method is superior to the existing method based on simulated annealing in terms of computational efficiency, and its accuracy is as well as the existing method under the same conditions. Our method enables us to perform constrained community detection for larger networks compared with the existing method.
    抄録全体を表示
  • 林 貴宏, 尾内 理紀夫
    30 巻 (2015) 1 号 p. 102-111
    公開日: 2015/01/06
    ジャーナル フリー
    This paper proposes a movie recommendation system using movie reviews on the Web. The system receives a movie review from a user, estimates the user's interests on movies from the review, and provides other persons' reviews to the user based on interest matching. This paper assumes that user's interests on movies appear on words which are positively or negatively evaluated in a review. Under the assumption, the system detects such words from the user's review, and chooses other persons' reviews to recommend in which the detected words are positively evaluated. Experimental results have shown that more than 1/3 of recommended reviews can motivate users to watch the movies mentioned in the reviews. In addition, the results have indicated that combining the proposed recommendation method and a conventional TF-IDF based recommendation method is important for more efficient recommendation.
    抄録全体を表示
  • Yuanyuan Wang, Yukiko Kawai, Kazutoshi Sumiya
    30 巻 (2015) 1 号 p. 112-123
    公開日: 2015/01/06
    ジャーナル フリー
    MOOC is a crucial platform for improving education; students are able to obtain various educational presentation contents through the Web. Recently, Prezi introduced a zoomable canvas as a substitute to the traditional presentations that allows users to zoom in and out of the presentation media. Teachers then attempt to provide presentations in a nonlinear fashion for enhancing the user interaction through these presentations; however, creation of nonlinear presentations would be time-consuming, besides posing design challenges. Therefore, we have developed a novel support system for grasping overviews of presentation slides, it generates a meaningfully structured presentation, called iPoster; this enables users to automatically navigate through the slide-based educational contents. The system places elements such as text and graphics of presentation slides in a structural layout by semantically analyzing the slide structure. The structural layout can reveal the hierarchy of elements based on topic structure by moving from the overview to a detail using automatic transitions, such as zooms and pans. Through this, the iPoster can support students to interactively browse online presentation slides for grasping an overview; it would substantially help the students navigate the presentation slides effectively for their learning purposes. In this paper, we discuss our interactive poster (iPoster) generation method and we have also included an evaluation of our method's effectiveness.
    抄録全体を表示
  • 土斐崎 龍一, 飯場 咲紀, 岡谷 貴之, 坂本 真樹
    30 巻 (2015) 1 号 p. 124-137
    公開日: 2015/01/06
    ジャーナル フリー
    With the widespread use of online shopping in recent years, consumer search requests for products have become more diverse. Previous web search methods have used adjectives as input by consumers. However, given that the number of adjectives that can be used to express textures is limited, it is debatable whether adjectives are capable of richly expressing variations of product textures. In Japanese, tactile and visual textures are easily and frequently expressed by onomatopoeia, such as ``fuwa-fuwa'' for a soft and light sensation and ``kira-kira'' for a glossy texture. Onomatopoeia are useful for understanding not only material textures but also a user's intuitive, sensitive, and even ambiguous feelings evoked by materials. In this study, we propose a system to rank FMD images corresponding to texture associated with Japanese onomatopoeia based on their symbolic sound associations between the onomatopoeia phonemes and the texture sensations. Our system quantitatively estimates the texture sensations of input onomatopoeia, and calculates the similarities between the users' impressions of the onomatopoeia and those of the images. Our system also suggests the images which best match the input onomatopoeia. An evaluation of our method revealed that the best performance was achieved when the SIFT features, the colors of the images, and text describing impressions of the images were used.
    抄録全体を表示
  • 高間 康史, 加藤 優, 桑折 章吾, 石川 博
    30 巻 (2015) 1 号 p. 138-147
    公開日: 2015/01/06
    ジャーナル フリー
    This paper proposes a search engine that is designed for answering trend-related queries. Recently, people can gather huge amount of information by using existing Web search engines. However, there is a significant difference between function provided by existing search engines and users' information needs. That is, a function of existing Web search engines is just to find Web pages containing keywords specified as a query. When we want to find some information from the Web, we have to break our information need into a series of queries by ourselves. As this process is burdensome for novices and even for experienced users, advanced search engine that can solve this problem should be realized. This paper focuses on the task of answering trend-related queries. By focusing on a specific task, proposed search engine can provide advanced search functions compared with existing Web search engines. At the same time, as this task is supposed to be useful in various domains, the proposed search engine can inherit one of important characteristics of existing search engines that it can be widely used regardless of domains. Prototype search engine collects various trend-information from the Web and provides three basic functions: a function for searching time periods when a query item had a characteristic trend, that for searching items having characteristic trend during query time period, and that for searching items having similar trend with query item. These functions are derived from analysis results of search intention using existing search engines, and users cans satisfy their various kinds of information needs related with trend information by combining those functions. The effectiveness of the prototype search engine is shown through experiments with test participants. Experimental results show that test participants can issue correct queries efficiently for given information needs. It is also shown that they can break their own information needs into a series of queries corresponding to various search intentions.
    抄録全体を表示
速報論文
  • 三宅 貫太郎, 福森 聡, 杉原 太郎, 五福 明夫, 佐藤 健治
    30 巻 (2015) 1 号 p. 148-151
    公開日: 2015/01/06
    ジャーナル フリー
    This article discusses the potential of Captology, a concept of the persuasive technologies, for long-term rehabilitation. Continuous rehabilitations to patients with chronic regional pain syndrome are an essential way to ameliorate the pain. Although the effects on a patient diminish when suspending the rehabilitation, he/she often feels resigned to keep it. Interference factors against the rehabilitation consist of difficulties to recognize the effects from the rehabilitation, interminable and repetitive rehabilitation, and complicated processes involving data collection for providing quality amelioration. Captology is one of promising concepts to solve these problems. We developed a set of functions with four principles from Captology, that is, Praise, Reduction, Tunneling and Self-Monitoring, into the system named VR/MVF for the sake of maintaining patient's motivation. One of the significant functions was developed to apply the principle of Praise. The system displays messages of praising/scolding to notice appropriate/inappropriate behaviors to him/her. The principles of Reduction and Tunneling were applied to reduce the burden of the system use. Tracking medical records by the principle of Self-Monitoring was employed to indicate the effects of rehabilitation to the patient.
    抄録全体を表示
原著論文
  • 岩崎 祐貴, 折原 良平, 清 雄一, 中川 博之, 田原 康之, 大須賀 昭彦
    30 巻 (2015) 1 号 p. 152-160
    公開日: 2015/01/06
    ジャーナル フリー
    Nowadays, anybody can easily express their opinion publicly through Consumer Generated Media. Because of this, a phenomenon of flooding criticism on the Internet, called flaming, frequently occurs. Although there are strong demands for flaming management, a service to reduce damage caused by a flaming after one occurs, it is very difficult to properly do so in practice. We are trying to keep the flaming from happening. It is necessary to identify the situation and the remark which are likely to cause flaming for our goal. Concretely, we propose methods to identify a potential tweet which will be a likely candidate of a flaming on Twitter, considering public opinion among Twitter users. Among three categories of flamings, our main focus is Struggles between Conflicting Values (SBCV), which is defined as a remark that forces one's own opinion about a topic on others. Forecasting of this type of flamings is potentially desired since most of its victims are celebrities, who need to care one's own social images. We proceed with a working hypothesis: a SBCV is caused by a gap between the polarity of the remark and that of public opinion. First, we have visualized the process how a remark gets flamed when its content is far from public opinion, by means of our original parameter daily polarity (dp). Second, we have built a highly accurate flaming prediction model with decision tree learning, using cumulative dp as an attribute along with parameters available from Twitter APIs. The experimental result suggests that the hypothesis is correct.
    抄録全体を表示
  • 吉田 光男, 荒瀬 由紀
    30 巻 (2015) 1 号 p. 161-171
    公開日: 2015/01/06
    ジャーナル フリー
    Query classification is an important technique for web search engines, allowing them to improve users' search experience. Specifically, query classification methods classify queries according to topical categories, such as celebrities and sports. Such category information is effective in improving web search results, online advertisements, and so on. Unlike previous studies, our research focuses on trend queries that have suddenly become popular and are extensively searched. Our aim is to classify such trend queries in a timely manner, i.e., classify the queries on the same day when they become popular, in order to provide a better search experience. To reduce the expensive manual annotation costs to train supervised learning methods, we focus on a label propagation method that belongs to the semi-supervised learning family. Specifically, the proposed method is based on our previous method that constructs a graph using a corpus, and propagates a small number of ground-truth categories of labeled queries in order to estimate the categories of unlabeled queries. We extend this method to cut ineffective edges to improve both classification accuracy and computational efficiency. Furthermore, we investigate in detail the effects of different corpora, i.e., web/blog/news search results, Tweets, and news pages, on the trend query classification task. Our experiments replicate the situation of an emerging trend query; the results show that web search results are the most effective for trend query classification, achieving a 50.1% F-score, which significantly outperforms the state-of-the-art method by 7.2 points. These results provide useful insights into selecting an appropriate dataset for query classification from the various types of data available.
    抄録全体を表示
  • 酒井 浩之, 西沢 裕子, 松並 祥吾, 坂地 泰紀
    30 巻 (2015) 1 号 p. 172-182
    公開日: 2015/01/06
    ジャーナル フリー
    In this paper, we propose a method of extracting causal information from PDF files of the summary of financial statements of companies, e.g., ''The sales of smart phones was expanded continually''. Cause information is useful for investors in selecting companies to invest. We downloaded 106,885 PDF files of the summary of financial statements of companies from Web pages of the companies automatically. Our method extracts causal information from the PDF files by using clue expressions (e.g., ''was expanded'') and keywords relevant to a company. The clue expressions are extracted from the PDF files of the summary of financial statements of companies and articles concerning business performance of companies automatically. We developed the search system which is able to retrieve causal informations extracted by our method. The search system shows causal information containing a keyword inputted by users, and the summary of financial statements containing the retrieved causal information. We evaluated our method and it attained 83.91% precision and 55.04% recall, respectively. Moreover, we compared our method with Sakai et al's method originally proposed for extracting causal information from financial articles concerning business performance of companies and experimental results showed that our method outperforms Sakai et al's method.
    抄録全体を表示
  • 杉山 弘晃, 目黒 豊美, 東中 竜一郎, 南 泰浩
    30 巻 (2015) 1 号 p. 183-194
    公開日: 2015/01/06
    ジャーナル フリー
    The development of open-domain conversational systems is difficult since user utterances are too flexible for such systems to respond properly. To address this flexibility, previous research on conversational systems has selected system utterances from web articles based on word-level similarity with user utterances; however, the generated utterances, which originally appeared in different contexts from the conversation, are likely to contain irrelevant information with respect to the input user utterance. To leverage the variety of web corpus in order to respond to the flexibility and suppress the irrelevant information simultaneously, we propose an approach that generates system utterances with two strongly related phrase pairs: one that composes the user utterance and another that has a dependency relation to the former. By retrieving the latter one from the web, our approach can generate system utterances that are related to the topics of user utterances. We examined the effectiveness of our approach with following two experiments. The first experiment, which examined the appropriateness of response utterances, showed that our proposed approach significantly outperformed other retrieval and rule-based approaches. The second one was a chat experiment with people, which showed that our approach demonstrated almost equal performance to a rule-based approach and outperformed other retrieval-based approaches.
    抄録全体を表示
  • 臼井 翔平, 鳥海 不二夫
    30 巻 (2015) 1 号 p. 195-203
    公開日: 2015/01/06
    ジャーナル フリー
    We analyze information diffusion by focusing on network structures. First, we propose a network growth model that produces networks with features required for analysis and perform a validation experiment using Twitter networks. The proposed model produces networks with features calculated from these real networks with high accuracy. Using this proposed model, we produce several networks that exhibit various features. We simulate information diffusion on these networks using an independent cascade (IC) model and calculate the Ability of Information Diffusion (AID). Second, we analyze how each feature affects information diffusion using this simulation. We found that the AID score was affected by the average shortest-path length L and variance of closeness centrality σι. We got a high AID score by a network with low L and σι.
    抄録全体を表示
論文特集「オノマトペの利活用」
原著論文
  • 前田 安里紗, 上間 大生, 白水 菜々重, 松下 光範
    30 巻 (2015) 1 号 p. 204-215
    公開日: 2015/01/06
    ジャーナル フリー
    The objective of this study is to support learning of Japanese onomatopoeia for foreigners who learn Japanese. In recent years, the number of such foreigners is increasing. There are a lot of onomatopoeia words in Japanese and many of them are difficult to translate because only the number of onomatopoeia words in foreign languages (e.g., Mandarin, Cantonese) are fewer than these in Japanese. To overcome the cultural difference, this paper proposes a digital picture book system for learning Japanese onomatopoeia. The system presents 32 onomatopoeia words to a user. The design criteria of the system is that: (1) adopts an interface of user participation, (2) presents a tiny story in which onomatopoeic words are associated with pictures, and (3) enables comparison of two synonymous/antomynic onomatopoeias. We conducted a user study with foreign learners and revealed that the proposed system improves understanding of semasiological differences between two confusing onomatopoeic words.
    抄録全体を表示
  • 加藤  亜由美, 深澤  佑介, 森  武俊
    30 巻 (2015) 1 号 p. 216-228
    公開日: 2015/01/06
    ジャーナル フリー
    Onomatopoeia appears much frequently in the word-of-mouth restaurant search site. In this paper, we first analyzed the relationship between food categories and onomatopoeias on the word-of-mouth restaurant search site. From the analysis, we found that the appearance of onomatopoeias and food categories are highly correlated. This fact indicates that na?ve way of using onomatopoeia as feature of restaurant makes the recommendation similar to food category based recommendation. This motivate us to develop sense related onomatopoeia based recommendation as senses plays an important role to enjoy food in restaurant. For the purpose, we propose an algorithm to collect sense related onomatopoeias from the web and produce serendipitous restaurant recommendation using sense related onomatopoeias as feature. We have conducted user test and the result shows that the recommendation using sense related onomatopoeia based recommendation satisfies 14 subjects from the viewpoint of serendipity, which is much larger than 3 subjects of food category based recommendation.
    抄録全体を表示
  • 石橋 賢, 深瀧 創, 宮田 一乘
    30 巻 (2015) 1 号 p. 229-236
    公開日: 2015/01/06
    ジャーナル フリー
    Recently, sizzle words have been utilized for various product packages. These words have effective communicative performance to convey deliciousness of food. In particular, onomatopoeias are used for many product packages because they can convey the texture of food sensuously. When using sizzle words, producers may consider consumers' impressions. This study aims to investigate the relations between consumers' impressions and sizzle words through an experiment. The experimental targets were four rice crackers of different hardness because their textures were directly related to consumers' impressions and some packages of rice crackers used a few sizzle words for advertising. The results of this experiment indicated five tendencies: (1) the sizzle words regarding satisfaction, tradition, and typicality, and the onomatopoeias including “zaku” are appropriate for an extremely hard rice cracker; (2) the sizzle words regarding lightness and comfort, and the onomatopoeias including “saku” are appropriate for a non-hard rice cracker; (3) the sizzle words regarding aridity, fineness, and unforgettable taste are appropriate for a slightly hard rice cracker; (4) the onomatopoeias expressing crunchy texture are appropriate for a quite hard rice cracker; (5) rough texture of food brings a sense of satiety. In addition, we performed a factor analysis using the results with 14 onomatopoeias in the experiment. The analysis results showed three factors: brittleness, irritation, and lightness. In future, we expect that these results can be utilized for guiding a choice of an appropriate sizzle word.
    抄録全体を表示
  • 鍵谷 龍樹, 白川 由貴, 土斐崎 龍一, 渡邊 淳司, 丸谷 和史, 河邉 隆寛, 坂本 真樹
    30 巻 (2015) 1 号 p. 237-245
    公開日: 2015/01/06
    ジャーナル フリー
    We feel some liquids such as honey or oil more viscous than others like water. Viscosity perception is frequently expressed by onomatopoeia, a set of words that are often used to express sensory experiences in Japanese. For example, we would say honey is “toro-toro” or oil is “doro-doro”. In this paper we investigated the associations between phonemes of Japanese onomatopoeia for expressing viscosity and subjective evaluations of viscosity. Specifically, we performed psychological experiments where participants watched some static images and dynamic images. Participants were asked to express the visual sensations by onomatopoeia and rate the degree to which they felt the objects viscous. This experiment was aimed at specifying the systematic association between phonemes of Japanese onomatopoeic words and viscous evaluations. Our results showed the existence of some associations between the phonemes of the words for expressing the sensation and the evaluations of viscosity and showed the possibility to construct a system to recommend viscosity animations by onomatopoeia. The system proposed in this paper recommends viscosity animations consistent with onomatopoetic expressions based on Japanese sound symbolism. Our system comprises a user interface module, an onomatopoeia parsing module, and a database. Our system can evaluate the subtle difference in viscosity feelings expressed by onomatopoeic words which are different in phonemes.
    抄録全体を表示
  • 内田 ゆず, 荒木 健治
    30 巻 (2015) 1 号 p. 246-256
    公開日: 2015/01/06
    ジャーナル フリー
    Nowadays, there are a number of product reviews on the Internet with the development of the consumer generated media as typified by social networking sites, blogs, and customer review sites. These reviews influence a consumer's buying decision and a company's market research. They are a lot valuable to both customers and companies, so that sentiment analysis becomes an active area of research. A sentiment polarity dictionary is essential to the sentiment analysis. We focus attention on onomatopoeia words in product reviews. It is noted that product reviews written by consumers in Japanese contain many onomatopoeia words. Japanese onomatopoeia can convey a subtle sense of features of products and customer's emotion. It is assumed that each onomatopoeia word in a product review provides a valuable clue to understanding a consumer's opinion. In this paper, we describe the appearance frequency of onomatopoeia words. After analysis of 729,865 reviews from Yahoo! Shopping, it is found that 482 words appeared in 52,121 reviews. We classify product categories in terms of the appearance frequency of onomatopoeia words with hierarchical cluster analysis and extract 978 pairs of product categories and onomatopoeia words which are likely connected to each other. Ten subjects judge the validity of these 978 pairs and consequently we conclude that 658 pairs are deemed appropriate for sentiment analysis. Further examination reveals the following two points: (1) it is highly possible that impressions of each product are described in the reviews containing onomatopoeias; and (2) the sentiment polarity of onomatopoeia differs depending on product categories.
    抄録全体を表示
  • 岡谷 英夫
    30 巻 (2015) 1 号 p. 257-264
    公開日: 2015/01/06
    ジャーナル フリー
    Sensory words such as onomatopoeia are difficult for students of Japanese because their cultures are different. How onomatopoeia are dealt with in elementary school compulsory education has been reviewed with the aim of considering how it can be applied to students of Japanese as a second language. Five Japanese textbooks that are currently in use at elementary schools for native speakers of Japanese were examined to see which onomatopoeic words appear and to what extent. A total of 6,443 onomatopoeic words were listed in these textbooks. Of the vast range of 6,443 words from the originally wide variety of words as counted from grade 1 to grade 6 from all the Japanese language textbooks, 92 were high-frequency onomatopoeic words which are proposed as the “basic onomatopoeia for beginners” as well as what kind of onomatopoeia and to what extent. These 92 high-frequency onomatopoeic words appeared 3,416 times, or 53.02% of the total 6,443 onomatopoeic words. If these 92 onomatopoeic words were studied, then over 50% of onomatopoeic words would be comprehensible to learners of Japanese. In addition, which verbs appear in conjunction with these onomatopoeic words together with their frequency are indicated.
    抄録全体を表示
  • 岩佐 和典, 小松 孝徳
    30 巻 (2015) 1 号 p. 265-273
    公開日: 2015/01/06
    ジャーナル フリー
    The purpose of this study was to investigate how the naming of an object influences visually induced tactile impression and emotional valence, using tactile sense-related onomatopoeic words for evaluation of tactile impression. The present study focused on how visually induced tactile impression and valence might differ when different names of the same visual texture were presented. In addition, to investigate the relationship between visually induced tactile impression and valence, correlations among change rates of tactile impression and valence induced by the alteration of names were examined. 60 undergraduate students (mean age = 19.55, male = 3, female = 57) participated in the experiment. The results revealed that different tactile impressions and emotional responses were evoked by the same visual texture when different names were presented. Moreover, significant correlations were found between change rates of tactile impression and valence. These results show that visually induced tactile impression and emotion are influenced by top-down semantic processes.
    抄録全体を表示
  • 平田 佐智子, 中村 聡史, 小松 孝徳, 秋田 喜美
    30 巻 (2015) 1 号 p. 274-281
    公開日: 2015/01/06
    ジャーナル フリー
    Japanese “onomatopoeic” words (also called mimetics and ideophones) are more frequent in spoken discourse, especially in informal daily conversations, than in writing. It is a common belief that onomatopoeia is particularly frequent in some areas, such as the Kinki region. To examine the plausibility of this folk dialectology, we investigated the frequency of onomatopoeia in the Minutes of the Diet as a corpus of spoken Japanese. We examined whether there is really a difference in the use of onomatopoeia among the eleven major regions of Japan. We analyzed the conversation data (limited to the last two decades) according to the hometowns of the speakers. The results revealed that there is no cross-regional difference in the overall frequency of onomatopoeia and non-onomatopoeic adverbs. However, a particular morphological type of onomatopoeia?i.e., “emphatic” onomatopoeia, such as hakkiri ‘clearly’?did show a regional variation in frequency. The results suggest that different types of onomatopoeia have different functions. The present study introduced a “macro-viewpoint” method that is based on a large-scale database. Further investigations into the functional aspect of onomatopoeia will also benefit from a dialectological method that adopts a “micro-viewpoint” on the detailed descriptions of a small number of speakers from each region. We hope that the present quantitative approach to the sociolinguistics of onomatopoeia will offer a new perspective on dialectology and on the effective utilization of onomatopoeia in the field of information science.
    抄録全体を表示
  • 田中 恒彦, 岡嶋 美代, 小松 孝徳
    30 巻 (2015) 1 号 p. 282-290
    公開日: 2015/01/06
    ジャーナル フリー
    We suggest as an important tool in psychotherapy the use of onomatopoeia. Mood disorder and Anxiety disorder are among the most prevalent mental disorders, and Behavior therapy (BT) is an evidence-based psychological treatment suitable for these cases. Interoceptive sensation is important in BT, because it serves as a barometer for responses. On the other hand, standard assessment methods such as subjects unit of disturbance scale (SUDs) is not optimal. In a different approach, we feel a certain form of it, e.g. Doki-Doki, at the same time when feeling emotion. However, the SUDs is assessed without taking somesthesis into consideration. In addition, BT requires information on somesthesis in order to optimally perform the therapy. Here we propose a solution to this problem, based on using onomatopoeia for SUDs. It can assess appropriately the interoceptive sensations by which a patient is accompanied in anxiety. We report two clinical cases using onomatopoeia for SUDs. This makes for an improved therapy. The internal sense appears during the course of the disease. A treatment is thus provided which is not tied to a diagnosis name, but rather by emphasizing the ``internal sense,'' which is more effective in producing an improvement towards curing.
    抄録全体を表示
  • 北條 宏季, 磯谷 順司, 戸本 裕太郎, 中村 剛士, 加納 政芳, 山田 晃嗣
    30 巻 (2015) 1 号 p. 291-305
    公開日: 2015/01/06
    ジャーナル フリー
    Embodied expertise, which expresses skills of experts, is a kind of tacit knowledge that is difficult to transfer from one person to another by writing it down or verbalizing it. The final goal of our study is to translate embodied expertise into explicit knowledge, i.e. onomatopoeias. We call the onomatopoeias ``embodied expertise onomatopoeias'', which can enable people to understand the skills intuitively and easily. For skillful actions to be translated into onomatopoeic words, we chose and adopted the writing operations of Japanese penmanship, Pen Shodo, using a pen. Japanese calligraphy using a brush, Shodo, is a popular art form in Japan. Pen Shodo is a similar art form, and improvement of Pen Shodo skills is useful for neat handwriting in business or daily life. Pen-writing skills are composed of several writing features. The important ones are the pen pressure that a writer puts on his/her pen and pen speed at which he/she writes. These two features greatly affect the appearance of Kanji characters written with a pen as well as Kanji characters written with a brush in traditional Shodo. In this paper, we investigated the correspondence between the writing features and onomatopoeic words. As the results, we detected some of the onomatopoeic words could affect the writing features. The investigation results might provide fundamental knowledge to verbalize embodied expertise into onomatopoeias.
    抄録全体を表示
  • 高丸 圭一, 内田 ゆず, 乙武 北斗, 木村 泰知
    30 巻 (2015) 1 号 p. 306-318
    公開日: 2015/01/06
    ジャーナル フリー
    An onomatopoeia is a useful linguistic expression to describe sounds, conditions, degrees and so on. It is said Japanese is rich in onomatopoeic expressions. They are frequently used in daily conversations. The meaning and surface structure of an onomatopoeia varies diachronically. There seem to be regional variations in usage of onomatopoeias. It is necessary to investigate the actual condition of onomatopoeia quantitatively in order to apply onomatopoeias into artificial intelligence. This paper studies practical usages of onomatopoeias in spoken modern Japanese language. To explore Japanese onomatopoeias nowadays, we investigate regional assembly minutes collected from all areas in Japan. The corpus of regional assembly minutes, which has about 300 million words, is the target of the investigation of this study. The minutes of Japanese regional assemblies contain all transcriptions of the utterances in the assemblies. This corpus is suitable for our research since attributes of the speakers are clear and speakers are distributed nation-wide. The first research is about total frequency and regional distribution of onomatopoeias. The onomatopoeias, which represent a request for a promotion of policy, e.g., ``shikkari'', ``dondon'', are used at high frequency in regional assemblies. There are no remarkable regional differences in frequencies of these onomatopoeias though western Japan has slight higher frequency. The second research is about the meaning of the onomatopoeias. Most of onomatopoeias are polysemous. The meaning of the onomatopoeia differs by context. The authors have manually checked through 10,827 sentences, which contain 153 kinds of onomatopoeia, and then classified the meaning of each onomatopoeic expression. We analyzed for the following subjects: i) ambiguity of onomatopoeic expression, ii) regional differences in meaning, iii) new meanings in modern spoken language, iv) special usage in assemblies, and v) onomatopoeias in the named entities. The third research is about false extraction of onomatopoeias in the morphological analysis. The extraction errors are analyzed from the viewpoint of surface structure and appearance position. In terms of surface structure, it is clear that the word length of an onomatopoeic expression, which has highly false extraction, is shorter. The onomatopoeic expressions, which end with special morae, namely moraic obstruent, moraic nasal and long vowel, have a higher rate of false extraction. In terms of appearance position, dialectal grammar is the main factor causing false extraction. About 25% of false extraction is found in the sentence-closing particles in dialectal grammar. The result of quantitative analysis of the onomatopoeia in modern spoken Japanese language serves as the basic data which contributes to engineering. The results of the analysis in our research are exhibited through the WWW. It is hoped that results will contribute broadly to the practical use of onomatopoeia in the engineering field.
    抄録全体を表示
  • 清水 祐一郎, 土斐崎 龍一, 鍵谷 龍樹, 坂本 真樹
    30 巻 (2015) 1 号 p. 319-330
    公開日: 2015/01/06
    ジャーナル フリー
    The present study proposes a method which generates Japanese onomatopoeia corresponding to impressions inputted by users. Japanese onomatopoeia is frequently used in comics and advertisements. Effective onomatopoeia in those fields are directly associated with sensuous experiences of readers or consumers, but it is very difficult to create such expressions. Therefore, the system which generates effective novel onomatopoeia corresponding to the impression specified by users has been expected to be as a technology which supports creators. Our system uses 43 SD scales as those expressing our intuitive impressions. These scales consist of scales expressing impressions of a haptic senses, visual senses and affective senses. Users of the system can choose the kinds of SD scales to be used to create onomatopoeia among from 1 to 43 SD scales. The system uses the genetic algorithm (GA) to create onomatopoeia corresponding to inputted impressions. We consider onomatopoeic expressions as a individuals of GA, which are expressed by an array of numerical values. Namely, each numerical value of an individual denotes each phonological symbol in Japanese. By comparing impressions inputted by user with those of each generated onomatopoeia, the system proposes onomatopoeia corresponding to impressions of users. The system evaluation showed that impressions of onomatopoeic expressions generated by our system were similar to the impressions inputted by users.
    抄録全体を表示
  • 楊 碩, 橋本 敬, 李 冠宏, 李 暁燕
    30 巻 (2015) 1 号 p. 331-339
    公開日: 2015/01/06
    ジャーナル フリー
    Japanese onomatopoeia is an important element to express feelings and experiences lively. It is very difficult for Japanese learners to acquire onomatopoeia, especially, its nuance. In this paper, based on traditional L2 learning theories, we propose a new learning method to improve the efficiency of learning Japanese onomatopoeias' nuance - both explicit and implicit - for non-native speakers. The method for learning implicit nuance of onomatopoeia consists of three elements. First is studying the formal rules representing the explicit nuances of onomatopoeic words. Second is creating new onomatopoeic words by learners to utilize those formal rules. The last is giving feedback of relevance of the onomatopoeias created. We then show a learning system implementing the proposed method. In addition, to verify the effectiveness of the proposed method and the learning system, we conducted an experiment involving two groups of subjects. While the experiment group covers all the three elements of the proposed method, the control group involves no creation process, which is supposed to be a core element of our proposed method, instead, does an assessment process in which the participants assess the appropriateness of onomatopoeic words presented. Both groups were required to take two tests, before and after going through the learning process. The learning effect is defined as the difference between the scores gained from pre-learning test and post-learning test. The result confirms that the proposed method has significant effect in learning onomatopoeia for non-native speakers. Moreover, the comparison against the control group shows that the creation process is the key to bring the learning effect.
    抄録全体を表示
  • 渡辺 知恵美, 中村 聡史
    30 巻 (2015) 1 号 p. 340-352
    公開日: 2015/01/06
    ジャーナル フリー
    This paper proposes a ranking methodology of cooking recipe by using fitness value between a recipe and onomatopoeia. This system is implemented as a function of a cooking recipe search site “Onomatoperori”. By using onomatopoeia, users can find what they want to cook from their ambiguous idea. We defined formulas for calculating fitness value between recipe and onomatopoeia by using mutual information between onomatopoeia and a word in title or description of recipes. In addition, we defined the similarity measure between onomatopeia words by mapping their words by using 15 sentimental dimensions for expressing the tastes and textures of the dishes. And we improve the ranking methodology by using the similarity among onomatopoeia words. By using these ranking methodologies we can search the cooking recipes which are related to the onomatopoeia although they do not include the onomatopeia word in the recipes.
    抄録全体を表示
  • 定延 利之
    30 巻 (2015) 1 号 p. 353-363
    公開日: 2015/01/06
    ジャーナル フリー
    In this paper, the author argues that mimetics are not morphological, syntactic, semantic phenomena by nature. Rather, they are a pragmatic behavior, spoken isolated from other sentential elements. This pragmatic behavior is characteristically performative (cf. Austin 1962). The performative characteristic of mimetics is utilized in the context of human play. This paper provides observations on this fact, and using the results of a questionnaire, it presents the possibility that machines may collaborate with humans by using mimetics in the manner of humans. More specifically, the following four points are examined: (i) The morphological, syntactic, semantic patterns often seen in mimetics, in which they are joined with other words in the sentence, such as an adjective noun, verb stem, or adverb, to illustrate or embellish descriptions more vividly, is not a characteristic of mimetics as they can be seen in other classifications of Japanese words, i.e. Yamato, Chinese, and foreign loan words, as well; (ii) In cases where mimetics are not joined with other words, they are spoken isolated from other sententil elements. This pragmatic behavior is hardly seen in other Yamato, Chinese, or foreign loan words and can be called a characteristic of mimetics. This pattern of verbal behavior in mimetics is performative (Austin 1962) on two points: first, if mimetics are not verbalized, the situation will not be apparent during the verbalization, and second, if mimetics are verbalized, this alone will make the situation apparent during the verbalization; (iii) This performative characteristic of mimetics is something that people utilize. One of the independent utterances of mimetics is used in the context of play, when acting as if some internal action had occurred in the speaker, although in fact no such action exists; (iv) There is the possibility that machines may collaborate with humans by using mimetics in the manner of humans. In other words, having machines use mimetics would evoke the context of play in the users; in that context, the machine would be able to act as if some internal action, as well as some physical action, had occurred, although in fact no such actions exist. This will cause the machine to give a cuter, more human, impression. A questionnaire survey conducted on 125 university students lends support to this idea.
    抄録全体を表示
  • 伊藤 惇貴, 加納 政芳, 中村 剛士, 小松 孝徳
    30 巻 (2015) 1 号 p. 364-371
    公開日: 2015/01/06
    ジャーナル フリー
    Onomatopoeias refer to words that represent the sound, appearance, or voice of things, which makes it possible to create expressions that bring a scene to life in a subtle fashion. Using onomatopoeias therefore makes process of robot motion generation more easily and intuitively. In previous research, objective quantified values of onomatopoeias have been used as indices of robot motion. In Japanese language, however, onomatopoeias also include mimetic and emotive words. Impression of these words arises from the experience of each people, therefore, its impression might differ among people. In this paper, we propose a method for adjusting the objective quantified values (sound symbolism attributes) of onomatopoeias. Using our method, users of robots are able to create its motions representing the user's image better.
    抄録全体を表示
論文特集「近未来チャレンジ 2013」
原著論文
  • 高間 康史, 串間 宗夫, 砂山 渡
    30 巻 (2015) 1 号 p. 372-382
    公開日: 2015/01/06
    ジャーナル フリー
    This paper proposes an analysis support tool for EMR (electronic medical record), based on which examines its applicability to EMR analysis task in a hospital. As the spread of EMR into hospitals, the demand for analyzing EMR for improving quality of medical care as well as for contributing to hospital management is increasing. Although application of data mining techniques is promising, it has not been so popular today. The proposed tool consists of two sub-tools: a tool for analyzing EMR with visualization, and that for adding technical terms to a dictionary used by a morphological analyzer. Those are developed on TETDM (Total Environment for Text Data Mining), which makes it possible for users to use multiple tools through unified interface. In order to examine the applicability of the proposed tools and TETDM to EMR analysis in a hospital, doctors and nurses in a hospital used the tool for analyzing actual EMR. The experimental result shows that they can analyze the difference between EMR written by novice nurses and veteran. It is also shown adding technical terms extracted from EMR is useful for improving the quality of text processing as well as for reducing ambiguity of terms.
    抄録全体を表示
  • 渡辺 健太郎, 西村 拓一, 本村 陽一, 持丸 正明
    30 巻 (2015) 1 号 p. 383-392
    公開日: 2015/01/06
    ジャーナル フリー
    The service industry takes a major role in the economic development. The enforcement of service activities in service fields is important for the further improvement of service productivity. For that purpose, it is effective to conduct the integrative development of service processes and support systems for them with the participation of stakeholders. Meanwhile, means to formalize and understand the current situations in service fields from multiple perspectives, such as how to collect data of service processes and how to analyze them have not been established yet. This causes the inefficiency of the development process. In this paper, the authors propose `COTO' database to collect data on service processes with multiple perspectives in an integrative manner and how it works to support the design of service processes and systems by employees. In addition, the authors propose service process patterns and a technology map to choose an adequate models and technologies for COTO database in response to features of service processes. Finally, the authors discuss how the proposed methods are applied to service cases and the future prospect of this research scheme.
    抄録全体を表示
  • 松本 慎平, 川口 大貴, 鳥海 不二夫
    30 巻 (2015) 1 号 p. 393-402
    公開日: 2015/01/15
    ジャーナル フリー
    At the time of the Great East Japan Earthquake, many Tweets of the disaster had been posted and Twitter had been effectively-utilized as an infrastructure for sharing disaster information and confirming safety. However in Twitter, there have been various kinds of information and also the volume is extremely huge, so a technology to effectively obtain the information on disaster or to filter users depending on their purpose of use are considered essential in order for Twitter to be effective at the time of disaster. Especially some kind of filtering mechanism to easily catch real humans' voices is assumed to be important for getting better performance out of Twitter at the time of disaster. The aim of this study is to numerically-express the characteristics of Twitter users by using the concept of entropy in response to each user's tweeting, replying, and retweeting activities, which are assumed to be the source of Twitter's real time feature, to show the details of Twitter users activities at the time of disaster, and to verify the possibility of this method for automatic user filtering. The real Twitter data distributed around the time of the earthquake is used to analyze, and especially in this paper, the difference of user attributes mainly between bot, cyborg and human is examined by using this data. From the experimental results, the characteristics of Twitter users were clarified with multidimensional quantitative values. The experimental results also showed the possibility for automatic user filtering.
    抄録全体を表示
    • |<
    • <
    • 1
    • >
    • >|
feedback
Top