Geierhos, Michaela; Bäumer, Frederik Simon; Schulze, Sabine; Stuß, Valentina
Document type:
Sammelbandbeitrag / Paper in Collective Volume
Title:
Filtering Reviews by Random Individual Error
Collection editors:
Ali, Moonis; Kwon, Young Sig; Lee, Chang-Hwan; Kim, Juntae; Kim, Yongdai
Title of conference publication:
Current Approaches in Applied Artificial Intelligence
Subtitle of conference publication:
28th International Conference on Industrial, Engineering and Other Applications of Applied Intelligent Systems, IEA/AIE 2015, Seoul, South Korea, June 10-12, 2015, Proceedings
Series title:
Lecture Notes in Computer Science; Lecture Notes in Artificial Intelligence
Series volume:
9101
Conference title:
International Conference on Industrial, Engineering and Other Applications of Applied Intelligent Systems (28., 2015, Seoul)
Conference title:
IEA/AIE 2015
Venue:
Seoul, South Korea
Year of conference:
2015
Date of conference beginning:
10.06.2015
Date of conference ending:
12.06.2015
Place of publication:
Cham
Publisher:
Springer
Year:
2015
Pages from - to:
305-315
Language:
Englisch
Abstract:
Opinion mining from physician rating websites depends on the quality of the extracted information. Sometimes reviews are user-error prone and the assigned stars or grades contradict the associated content. We therefore aim at detecting random individual error within reviews. Such errors comprise the disagreement in polarity of review texts and the respective ratings. The challenges that thereby arise are (1) the content and sentiment analysis of the review texts and (2) the removal of the random individual errors contained therein. To solve these tasks, we assign polarities to automatically recognized opinion phrases in reviews and then check for divergence in rating and text polarity. The novelty of our approach is that we improve user-generated data quality by excluding error-prone reviews on German physician websites from average ratings. «
Opinion mining from physician rating websites depends on the quality of the extracted information. Sometimes reviews are user-error prone and the assigned stars or grades contradict the associated content. We therefore aim at detecting random individual error within reviews. Such errors comprise the disagreement in polarity of review texts and the respective ratings. The challenges that thereby arise are (1) the content and sentiment analysis of the review texts and (2) the removal of the random... »