The Community for Technology Leaders
2016 5th IIAI International Congress on Advanced Applied Informatics (IIAI-AAI) (2016)
Kumamoto, Japan
July 10, 2016 to July 14, 2016
ISBN: 978-1-4673-8986-0
pp: 31-36
Sarcasm presents a negative meaning with positive expressions and is a non-literalistic expression. Sarcasm detection is an important task because it contributes directly to the improvement of the accuracy of sentiment analysis tasks. In this study, we propose a extraction method of sarcastic sentences in product reviews. First, we analyze sarcastic sentences in product reviews and classify the sentences into 8 classes by focusing on evaluation expressions. Next, we generate classification rules for each class and use them to extract sarcastic sentences. Our method consists of three stage, judgment processes based on rules for 8 classes, boosting rules and rejection rules. In the experiment, we compare our method with a baseline based on a simple rule. The experimental result shows the effectiveness of our method.
Sentiment analysis, Boosting, Feature extraction, Syntactics, Focusing, Dictionaries, Informatics,Rule-based method, Sarcasm detection, Classification, Sentiment analysis
Satoshi Hiai, Kazutaka Shimada, "A Sarcasm Extraction Method Based on Patterns of Evaluation Expressions", 2016 5th IIAI International Congress on Advanced Applied Informatics (IIAI-AAI), vol. 00, no. , pp. 31-36, 2016, doi:10.1109/IIAI-AAI.2016.198
172 ms
(Ver 3.3 (11022016))