Root Cause Analysis Based on Relations Among Sentiment Words

Abstract

Sentiment analysis is a useful method to extract user preferences from product reviews; however, it cannot explain the detailed reasons for user preferences because of the exclusion of neutral sentiment words, constituting a large proportion of the words used in reviews. In contrast, there are limitations to using root cause analysis to analyze sentiment relations using sentiment words extracted from user preferences. This research aimed to extract a more fine-grained root cause by proposing a novel method capable of analyzing the root cause based on the relations between sentiment words. To identify the root causes of negative opinions in aspect-level sentiment analysis, we analyze the hierarchical and causal relations between sentiment triples and utilize hierarchical clustering based on sentiment triples’ relation to compensate for general sentiment words. The experimental results showed that the proposed method was 6.4% and 5.1% more accurate than the existing aspect-level analysis for the mobile device and clothing domains, respectively. Finally, we discussed some issues associated with the proposed method using a qualitative evaluation. In this study, a novel root cause identification method that can utilize the hierarchical and causal relations between sentiment words using negative and neutral sentiment expressions of product reviews is proposed.