Relational Features in Fine-Grained Opinion Analysis

Abstract

Fine-grained opinion analysis methods often make use of linguistic features but typically do not take the interaction between opinions into account. This article describes a set of experiments that demonstrate that relational features, mainly derived from dependency-syntactic and semantic role structures, can significantly improve the performance of automatic systems for a number of fine-grained opinion analysis tasks: marking up opinion expressions, finding opinion holders, and determining the polarities of opinion expressions. These features make it possible to model the way opinions expressed in natural-language discourse interact in a sentence over arbitrary distances. The use of relations requires us to consider multiple opinions simultaneously, which makes the search for the optimal analysis intractable. However, a reranker can be used as a sufficiently accurate and efficient approximation.A number of feature sets and machine learning approaches for the rerankers are evaluated. For the task of opinion expression extraction, the best model shows a 10-point absolute improvement in soft recall on the MPQA corpus over a conventional sequence labeler based on local contextual features, while precision decreases only slightly. Significant improvements are also seen for the extended tasks where holders and polarities are considered: 10 and 7 points in recall, respectively. In addition, the systems outperform previously published results for unlabeled (6 F-measure points) and polarity-labeled (10-15 points) opinion expression extraction. Finally, as an extrinsic evaluation, the extracted MPQA-style opinion expressions are used in practical opinion mining tasks. In all scenarios considered, the machine learning features derived from the opinion expressions lead to statistically significant improvements.

Understanding Gating Operations in Recurrent Neural Networks through Opinion Expression Extraction

“…Choi and Cardie take attributes (polarity and intensity) of opinion expressions into consideration and improve both tasks of opinion expression identification and attribute prediction within a joint model [11]. Johansson and Moschitti extract relational features of polarity pairs from the syntactic and semantic analysis result and show that this interaction information brings obvious improvement [12,13]. Yang and Cardie formulate the opinion expression extraction and attribute classification as a segmentation problem and segment attribute classification [14].…”

Aligning Opinions: Cross-Lingual Opinion Mining with Dependencies

“…Choi et al (2005) and Breck et al (2007) used CRFs for finding opinion holders and recognizing opinion expressions, respectively. The two things are predicted jointly by Choi et al (2006), with integer programming, and Johansson and Moschitti (2010), via reranking. The same method was applied later for joint prediction of opinion expressions and their polarities (Johansson and Moschitti, 2011).…”

Opinion Holder and Target Extraction for Verb-based Opinion Predicates – The Problem is Not Solved

“…For our experiments, we use the sequence labeler from Johansson and Moschitti (2013), Mul-5 The split-up of training and test set on the MPQA corpus follows the specification of Johansson and Moschitti (2013). Table 6: F-scores of opinion-holder classifiers on the MPQA corpus and the new VERB corpus.…”