Journal of Japan Society for Fuzzy Theory and Intelligent Informatics
Online ISSN : 1881-7203
Print ISSN : 1347-7986
ISSN-L : 1347-7986
Volume 27 , Issue 3
Showing 1-14 articles out of 14 articles from the selected issue
Regular
Original Papers
  • Tatsuya SENBON, Kazuhiro TAKEUCHI
    2015 Volume 27 Issue 3 Pages 627-637
    Published: June 15, 2015
    Released: June 30, 2015
    JOURNALS FREE ACCESS
    Compared with computational language resources in English, word knowledge in Japanese for sentiment analysis is relatively under-developed. Sentiment axes have been used in Japanese psychological questionnaires for many years, and in this paper, we employ these axes for specific antonym relations in a word-relation network. The initial network is trained using target documents for sentiment analysis. We evaluate this trained word-relation network in several ways. First, we compare our results with a major sentiment-polarity dictionary. Then, we analyze the ex-tracted sentiment axes in each domain subjectively, along with the network's performance in predicting the grading of the reviews.
    Download PDF (2066K)
  • Tomohiro HAYASHIDA, Ichiro NISHIZAKI, Akie SUEMUNE
    2015 Volume 27 Issue 3 Pages 638-649
    Published: June 15, 2015
    Released: June 30, 2015
    JOURNALS FREE ACCESS
    A recurrent neural network which its structure and link weights between units are appropriately determined has the ability to adequately predict for time-series data. It is difficult to find an optimal structure of the recurrent neural network minimizing both of the training and the generalization errors. In this paper, we propose an optimization method for structural design of neural networks for time-series data by employing tabu search with efficient neigh-borhood search. To demonstrate the efficiency and effectiveness of the proposed method, we apply our method to several benchmark problems of time-series data and it delivers superior or equal performance to other existing struc-tural optimization methods.
    Download PDF (936K)
feedback
Top