Toward advice mining: advanced conditional random fields for extracting advice-revealing text units

Abstract

Web forums often contain explicit key learnings gleaned from people`s experiences since they are platforms for personal communications on sharing information with others. One of the key learnings contained in Web forums is often expressed in the form of advice. In this paper, we address the problem of advice-revealing text unit (ATU) extraction from online forums due to its usefulness in travel domain. We represent an advice as a two-tuple comprising an advice-revealing sentence and its context sentences. To extract the advice-revealing sentences, we propose to define the problem as a sequence labeling problem, using three different types of features: syntactic, contextual, and semantic features. We also improve the performance using Skip-Chain CRF in which our sentence generalization method is employed to construct the skip-edges. To extract the context sentences, we propose to use 2D-CRF model, which gives the best performance compared to traditional machine learning models. Finally, we present an integrated solution to extract advice-revealing sentences and their respective context sentences at the same time using our proposed models, i.e., Multiple Linear CRF (ML-CRF) and 2 Dimensional CRF Plus (2D-CRF+). The experiment results show that ML-CRF performs better than any other models for extracting advice-revealing sentences and context sentences.