Opinion observer: analyzing and comparing opinions on the Web
WWW '05 Proceedings of the 14th international conference on World Wide Web
Opinion Mining and Sentiment Analysis
Foundations and Trends in Information Retrieval
Latent aspect rating analysis on review text data: a rating regression approach
Proceedings of the 16th ACM SIGKDD international conference on Knowledge discovery and data mining
Proceedings of the SIGCHI Conference on Human Factors in Computing Systems
Hi-index | 0.00 |
Review Explorer is an interface that utilizes categorized information to help users to explore a huge amount of online reviews more easily. It allows users to sort entities (e.g. restaurants, products) based on their ratings of different aspects (e.g. food for restaurants) and highlight sentences that are related to the selected aspect. Existing interfaces that summarize the aspect information in reviews suffer from the erroneous predictions made by the systems. To solve this problem, Review Explorer performs a real-time aspect sentiment analysis when a reviewer is composing a review and provides an interface for the reviewer to easily correct the errors. This novel design motivates reviewers to provide corrected aspect sentiment labels, which enables our system to provide more accurate information than existing interfaces.