Thumbs up or thumbs down?: semantic orientation applied to unsupervised classification of reviews
ACL '02 Proceedings of the 40th Annual Meeting on Association for Computational Linguistics
Thumbs up?: sentiment classification using machine learning techniques
EMNLP '02 Proceedings of the ACL-02 conference on Empirical methods in natural language processing - Volume 10
ACL '05 Proceedings of the 43rd Annual Meeting on Association for Computational Linguistics
Designing novel review ranking systems: predicting the usefulness and impact of reviews
Proceedings of the ninth international conference on Electronic commerce
Sentiment in short strength detection informal text
Journal of the American Society for Information Science and Technology
| Hi-index | 0.00 |
In the NLP field, there have been a lot of works which focus on the reviewer's point of view conducted on sentiment analyses, which ranges from trying to estimate the reviewer's score. However the reviews are used by the readers. The reviews that give a big influence to the readers should have the highest value, rather than the reviews to which was assigned the highest score by the writer. In this paper, we conducted the analyses using the reader's point of view. We asked 20 subjects to read 500 sentences in the reviews of Rakuten travel and extracted the sentences that gave a big influence to the subjects. We analyze the influential sentences from the following two points of view, 1) targets and evaluations and 2) personal tastes. We found that "room", "service", "meal" and "scenery" are important targets which are items included in the reviews, and that "features" and "human senses" are important evaluations which express sentiment or explain targets. Also we showed personal tastes appeared on "meal" and "service".