Semantics-driven implicit aspect detection in consumer reviews
With consumer reviews becoming a mainstream part of e- commerce, a good method of detecting the product or ser- vice aspects that are discussed is desirable. This work fo- cuses on detecting aspects that are not literally mentioned in the text, or implicit aspects. To this end, a co-occurrence matrix of synsets from WordNet and implicit aspects is con- structed. The semantic relations that exist between synsets in WordNet are exploited to enrich the co-occurrence matrix with more contextual information. Comparing this method with a similar method which is not semantics-driven clearly shows the bene t of the proposed method. Especially cor- pora of limited size seem to bene t from the added semantic context.
|Organisation||Erasmus University Rotterdam|
Schouten, K.I.M, De Boer, N, Lam, T, Van Leeuwen, M, Van Luijk, R, & Frasincar, F. (2015). Semantics-driven implicit aspect detection in consumer reviews. doi:10.1145/2740908.2742734