Automatic generation of short informative sentiment summaries

In this paper, we define a new type of summary for sentiment analysis: a singlesentence summary that consists of a supporting sentence that conveys the overall sentiment of a review as well as a convincing reason for this sentiment. We present a system for extracting supporting sentences from online product reviews, based on a simple and unsupervised method. We design a novel comparative evaluation method for summarization, using a crowdsourcing service. The evaluation shows that our sentence extraction method performs better than a baseline of taking the sentence with the strongest sentiment.