Automatically Evaluating Opinion Prevalence in Opinion Summarization

When faced with a large number of product reviews, it is not clear that a human can remember all of them and weight opinions representatively to write a good reference summary. Wepropose an automatic metric to test the prevalence of the opinions that a summary expresses, based on counting the number of reviews that are consistent with each statement in the summary, while discrediting trivial or redundant statements. To formulate this opinion prevalence metric, we consider several existing methods to score the factual consistency of a summary statement with respect to each individual source review. On a corpus of Amazon product reviews, we gather multiple human judgments of the opinion consistency, to determinewhich automatic metric best expresses consistency in product reviews. Using the resulting opinion prevalence metric, we show that a human authored summary has only slightly betteropinion prevalence than randomly selected extracts from the source reviews, and previous extractive and abstractive unsupervised opinion summarization methods perform worse thanhumans. We demonstrate room for improvement with a greedy construction of extractive summaries with twice the opinion prevalence achieved by humans. Finally, we show that pre-processing source reviews by simplification can raise the opinion prevalence achieved by existing abstractive opinion summarization systems to the level of human performance