Evaluative Language Beyond Bags of Words: Linguistic Insights and Computational Applications

Evaluative Language Beyond Bags of Words: Linguistic Insights and Computational Applications Farah Benamara∗ IRIT-Universit´e de Toulouse Maite Taboada∗∗ Simon Fraser University Yannick Mathieu† LLF-CNRS The study of evaluation, affect, and subjectivity is a multidisciplinary enterprise, including sociology, psychology, economics, linguistics, and computer science. A number of excellent computational linguistics and linguistic surveys of the field exist. Most surveys, however, do not bring the two disciplines together to show how methods from linguistics can benefit computational sentiment analysis systems. In this survey, we show how incorporating linguistic insights, discourse information, and other contextual phenomena, in combination with the statistical exploitation of data, can result in an improvement over approaches that take advantage of only one of these perspectives. We first provide a comprehensive introduction to evaluative language from both a linguistic and computational perspective. We then argue that the standard computational definition of the concept of evaluative language neglects the dynamic nature of evaluation, in which the interpretation of a given evaluation depends on linguistic and extra- linguistic contextual factors. We thus propose a dynamic definition that incorporates update functions. The update functions allow for different contextual aspects to be incorporated into the calculation of sentiment for evaluative words or expressions, and can be applied at all levels of discourse. We explore each level and highlight which linguistic aspects contribute to accurate extraction of sentiment. We end the review by outlining what we believe the future directions of sentiment analysis are, and the role that discourse and contextual information need to play. ∗ 118 Route de Narbonne, 31062 Toulouse, France. E-mail: benamara@irit.fr. ∗∗ 8888 University Dr., Burnaby, BC, V5A 1S6, Canada. E-mail: mtaboada@sfu.ca. † Universit´e Paris 7, Paris Diderot, Bat. Olympe de Gouges 8 place Paul Ricœr, case 7031, 75205 Paris Cedex 13, France. E-mail: ymathieu@linguist.univ-paris-diderot.fr. Submission received: 30 October 2015; revised version received: 19 February 2016; accepted for publication: 8 June 2016. doi:10.1162/COLI a 00278 © 2017 Association for Computational Linguistics Published under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International (CC BY-NC-ND 4.0) license Computational Linguistics Volume 43, Number 1 1. Introduction Evaluation aspects of language allow us to convey feelings, assessments of people, situations and objects, and to share and contrast those opinions with other speakers. An increased interest in subjectivity, evaluation, and opinion can be viewed as part of what has been termed the affective turn in philosophy, sociology, and political science (Clough and Halley 2007), and affective computing in artificial intelligence (Picard 1997). This interest has met with the rise of the social web, and the possibility of widely broadcasting emotions, evaluations, and opinions. The study of evaluation, affect, and subjectivity is a multidisciplinary enterprise, including sociology (Voas 2014), psychology (Ortony et al. 1988; Davidson et al. 2003), economics (Rick and Loewenstein 2008), and computer science (Pang and Lee 2008; Scherer et al. 2010; Cambria and Hussain 2012; Liu 2012, 2015). In linguistics, studies have been framed within a wide range of theories, such as Appraisal theory (Martin and White 2005), stance (Biber and Finegan 1989), evaluation (Hunston …

Content truncated to 500 words