Polarity classification (positive, negative or neutral opinion detection) is well developed in the field of opinion mining. However, existing tools, which perform with high accuracy on short sentences and explicit expressions, have limited success interpreting narrative phrases and inference contexts. In this article, we will discuss an important aspect of opinion mining: inference. We will give our definition of inference, classify different types, provide an annotation framework and analyze the annotation results. While inferences are often studied in the field of Natural-language understanding (NLU), we propose to examine inference as it relates to opinion mining. Firstly, based on linguistic analysis, we clarify what kind of sentence contains an inference. We define five types of inference: logical inference, pragmatic inference, lexical inference, enunciative inference and discursive inference. Second, we explain our annotation framework which includes both inference detection and opinion mining. In short, this manual annotation determines whether or not a target contains an inference. If so, we then define inference type, polarity and topic. Using the results of this annotation, we observed several correlation relations which will be used to determine distinctive features for automatic inference classification in further research. We also demonstrate the results of three preliminary classification experiments.
Analysis of Inferences in Chinese for Opinion Mining Opinion mining is an essential activity for economic watch, made easier by social networks and ad hoc forums. The analysis generally relies on lexicon of sentiments. Nevertheless, some opinions are expressed through inferences. In this paper, we propose a classification of inferences used in Chinese in tourist comments, for an opinion mining task, based on three levels of analysis (semantic realization, modality of realization and production mode). We proved the interest to analyze the distinct types of inferences to identify the polarity of opinions expressed in corpora. We also present some results based on word embeddings.