Interactive public comment is a method for public involvement which authors have developed, the aim of which is to collect citizens' opinions, and summarize and deliver them to administrators. Opinions collected at such workshops, however, very often contain a lot of "untamed" expressions, contrastive to professional terms familiar to most of administrators, and then requiring sensitive handling by operators. Through analyzing examples of those expressions observed in fieldwork, this article exhibits a possibility that these untamed expressions are not addressed to the facilitator of the workshop but rather to other co-participants who sometimes have co-membership with the speaker and are adopted in order to elicit empathy with and affirmation about the opinions from them, and argues that it therefore is necessary to devise some ways to appropriately utilize advantages of such untamed expressions.

In this paper, we introduce an annotation scheme for body movement based on participants' understandings in interaction. In previous studies of annotation scheme for building a dialogue system, labels which labelers put on a software were determined in advance. In our annotation scheme, we use a form of sentence to describe body movements and set two kinds of hierachical-related tiers; upper tier for interactional practice and lower tier for psysical practice. And we set meta-level tier in order to observe a relationship between modalities. We believe that it is useful information to detect similar expressions and sequential pattern of multimodal interactions.

In this paper, we describe how the participants organize the "modification" of body movement in dental interaction. Unlike "repair" in conversation, modification in embodied interaction is organized owing to whether each participant has three kinds of competence, i.e., physical competence, cognitive competence, and institutional competence. Four excerpts from dental interactions are analyzed from the viewpoint of who initiates and who performs the modification.

In this paper, we report on a diachronic study of "San'yako," people who are engaged in Nozawa-onsen Dosojin festival. They are working together for three years for the preparation of each year's festival, such as logging and timber processing and construction of a big shrine pavilion. In the first year, they sometimes stand awkwardly, failing to find what to do, but in the subsequent years, they can get actively involved in a task at hand. We show how they develop these skills, by understanding a sense of values behind such skills, based on the interactional data obtained from our longitudinal recordings of the field.

We discuss fieldwork methods that make happy both researchers and local people by contrasting the difference between the two authors' fields. As a case study, we report our experience in our fields (Ishigaki in Okinawa and Nozawa in Nagano) through interactions between local people. We contrast our methods depending on the goals, characteristics of the fields, and how we interact with the local people, suggesting what we can do for them.

Conversations in business plan consultation sessions were analyzed in terms of the concern-alignment model of consensus-building dialogues. The concern-alignment model stipulates a set of high-level dialogue acts for proposals and concerns, and dialogue structures in consultation conversations were described as joint exploration in the space of possible concerns to seek optimal business plans through consultation sessions. A focus of this report is to examine variations in manual coding across annotators and devise a method to ensure reliability of concern annotations.

There is a growing interest in conversation agents which conduct attentive listening. However, the current conversation agents always generate the same or limited form of backchannels every time, giving a monotonous impression. We have investigated generation of a variety of backchannels according to the dialogue context using the corpus of counseling dialogue. At first, we annotate all acceptable backchannel form categories considering the arbitrary nature of backchannels. Then, we conduct machine learning to predict a backchannel form from the linguistic and prosodic features of the preceding context. This model outperformed the method which always outputs the same form of backchannels and also the method which randomly generates backchannels. Finally, subjective evaluations by human listeners show that the proposed method generates backchannels more naturally giving a feeling of understanding and empathy.

Backchannels, as an exemplary dialog phenomenon, have received much attention, but the details of their forms and functions are still not well understood. We examined the prosodic properties of 280 backchannel tokens annotated as "un" or "u:n". In addition to the expected difference in length, there was a difference in pitch: whereas the "un" tokens had falling pitch, the pitch of the "u:n" tokens was closer to flat. One way to describe this difference is to postulate that "un" has a lexical accent but "u-n"does not. We discuss the implications for transcription standards and for modeling.

In spoken dialogue systems, especially chatting systems, smooth turn-taking function is one of the most important techniques to realize natural interaction with users. Fillers are presumed to play an important role in natural turn-taking in human dialogue. To this end, in this study, we analyzed a dialogue corpus where people talk with a humanoid android ERICA which was remotely operated. At first, we examined the occurrence rate of fillers at clause units in the case of turn-taking or not. The results suggest that we can see some differences among the roles of the participants. Next, some functions of each filler form were analyzed, which suggests a possibility that forms of fillers can be predicted using an adjacency pair.

We analyzed the processes by which people achieve speech-based navigation tasks under the shared situation using the Konbini Corpus [Raux 10]. We observed that there were several behaviors, interactions and communications that could not be explained by existing theories. Existing theories assume that people need to share their plans in order to achieve their common goal. (e.g. Shared Plan model: [Cohen 91, Grosz 90, Traum 94]). On the contrary to those theories, the participants in the Konbini Corpus successfully achieved their common goal without developing clear mutual beliefs about their goals nor plans. The results showed that participants usually started their actions without developing concrete mutual beliefs, and their actions were either self-corrected or interposed by other members in the middle of the actions. In order to explain these results, we proposed necessary requirements for a new model.

A university and B university have worked the research project, which aim to establish the steady supply system of the scallop in cooperation with fishermen and private companies. Both universities held the workshop to appropriately grasp the needs of fishermen who are main users of the support tools. We recorded the state, activity and interaction of participants using video cameras and wearable cameras. Thus, an interactive relationship and situation is made clear, thus indicating the state of the other participant during the proceeding with the workshop by the facilitator.

Many researches support farmers to collect physiological and environmental data automatically to increase the value of agricultural products. In the research area of a field monitoring, this paper describes agricultural field monitoring works and field sensing gadgets. We have developed field monitoring systems with high definition digital cameras and various types of field sensing gadgets such as a hand framing camera and smartphone based spectrometer. Collected data such as image and sensor values are transferred to cloud services such as Flickr and Twitter from the devices through the Internet. Our system can realize low cost and high quality field monitoring.

地域づくりのフィールドでは、定量的計測とは別に、非数値的な対話法や対話技術の研究が模索されている。人工知能の分野でも、開発技術をどのように実用や現場に適合させるのかという課題がある。本論では、こうした課題を視野に、地域づくりの対話現場での、音声言語認識や文字識別などデジタル処理技術の活用場面を提案する。