Seeing Stars from Reviews by a Semantic-based Approach with MapReduce Implementation
Pengfei Liu, Xiaojun Qian, Helen M. L. Meng · 2014
This study concerns the problem of aspect-level opinion (sen-timent) mining from online reviews. The problem consists of two fundamental sub-tasks: aspect extraction (identify specific aspects of the product from reviews), and aspect rating estima-tion (offer a numerical rating for each aspect). Solving this prob-lem is important and useful for many applications, e.g., providing aspect-level review summaries to consumers for better decision making, and for product manufacturers to collect summarized user feedback. Our objective is to propose a semantic-based ap-proach for aspect level opinion mining from massive amounts of reviews in a scalable fashion. The MapReduce implemen-tation for this approach obtains much runtime reduction com-pared with the single-process implementation. Experimental re-sults show that the runtime reductions by the MapReduce im-plementation are almost linear to the number of mappers, e.g., around 7.4 times reduction with 10 mappers on the TripAdvi-sor dataset and 2.6 times reduction with 4 mappers on the Yelp dataset. The number of mappers and reducers can be config-ured on demand to handle very large datasets in a scalable fash-ion. Moreover, the semantic-based approach obtains good per-formance for aspect rating estimation on the TripAdvisor dataset, with the MAE score of around 1.0 on all aspects, which means that the average deviation between the human rating and the esti-mated rating is around 1 star. The source code of our implemen-tation for the sentiment-based approach can be downloaded from