Farah Benamara

Measuring the effect of discourse structure on sentiment analysis

The aim of this paper is twofold: measuring the effect of discourse structure when assessing the overall opinion of a document and analyzing to what extent these effects depend on the corpus genre. Using Segmented Discourse Representation Theory as our formal framework, we propose several strategies to compute the overall rating. Our results show that discourse-based strategies lead to better scores in terms of accuracy and Pearsons correlation than state-of-the-art approaches.

Mapping Different Rhetorical Relation Annotations: A Proposal

Annotation efforts have resulted in the availability of a number of corpora with rhetorical relation information. The corpora, unfortunately, are annotated under different theoretical approaches and have different hierarchie of relations. In addition, new sets of rhetorical relations have been proposed to accounfor language variation. The types of relations, however, tend to overlap or be related in specific ways. We believe that differences across approaches are minimal, and a unified set of relations that works across languages is possible. This paper details a new taxonomy of relations organized in four top level-classes with a total of 26 relations. We propose a mapping between existing annotations and show that our taxonomy is robust across theories, and can be applied to multiple languages.

Evaluative language beyond bags of words: Linguistic insights and computational applications

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.

Preference extraction from negotiation dialogues

This paper presents an NLP-based approach to extracting preferences from negotiation dialogues. We propose a new annotation scheme to study how preferences are linguistically expressed on two different corpus genres. We then automatically extract preferences in two steps: first, we extract the set of outcomes; then, we identify how these outcomes are ordered. We finally assess the reliability of our method on each corpus genre.

Lexicalisation strategies in cooperative question-answering systems

In this project note, we present the main features of lexicalisation strategies deployed by humans in question-answering (QA) tasks. We then show how these can be reproduced in automated QA systems, in particular in Intelligent Cooperative Question-Answering Systems.

Assessing Opinions in Texts

This chapter focuses on measuring the effect of discourse structure on sentiment analysis. Discourse structure is essential in determining the content conveyed by a text. It affects for example, the temporal structure of a text, the interpretation of anaphoric expressions and pre-suppositions. Discourse structure has been shown to be useful in many NLP applications, such as automatic text summarization and textual entailment. This chapter focuses on measuring the effect of discourse structure on sentiment analysis. It presents the annotation scheme and then describes the corpus. The chapter presents the data, and describes the annotation campaign. It then gives the results of annotation campaign along with the observations. The sentence level is not appropriate for analyzing opinions in discourse since, in addition to objective clauses, a single sentence may contain several opinion clauses that can be connected by rhetorical relations. Keywords: anaphoric expressions; annotation campaign; discourse structure; NLP applications; opinions; presuppositions; sentiment analysis

Individual opinions-based judgment aggregation procedures

Judgment aggregation is a recent formal discipline that studies how to aggregate individual judgments on logically connected propositions to form collective decisions on the same propositions. Despite the apparent simplicity of the problem, the aggregation of individual judgments can result in an inconsistent outcome. This seriously troubles this research field. Expert panels, legal courts, boards, and councils are only some examples of group decision situations that confront themselves with such aggregation problems. So far, the existing framework and procedures considered in the literature are idealized. Our goal is to enrich standard judgment aggregation by allowing the individuals to agree or disagree on the decision rule. Moreover, the group members have the possibility to abstain or express neutral judgments. This provides a more realistic framework and, at the same time, consents the definition of an aggregation procedure that escapes the inconsistent group outcome.

COOPML: towards annotating cooperative discourse

In this paper, we present a preliminary version of COOPML, a language designed for annotating cooperative discourse. We investigate the different linguistic marks that identify and characterize the different forms of cooperativity found in written texts from FAQs, Forums and emails.

Introduction to the Special Issue on Language in Social Media: Exploiting Discourse and Other Contextual Information

Social media content is changing the way people interact with each other and share information, personal messages, and opinions about situations, objects, and past experiences. Most social media texts are short online conversational posts or comments that do not contain enough information for natural language processing (NLP) tools, as they are often accompanied by non-linguistic contextual information, including meta-data (e.g., the user’s profile, the social network of the user, and their interactions with other users). Exploiting such different types of context and their interactions makes the automatic processing of social media texts a challenging research task. Indeed, simply applying traditional text mining tools is clearly sub-optimal, as, typically, these tools take into account neither the interactive dimension nor the particular nature of this data, which shares properties with both spoken and written language. This special issue contributes to a deeper understanding of the role of these interactions to process social media data from a new perspective in discourse interpretation. This introduction first provides the necessary background to understand what context is from both the linguistic and computational linguistic perspectives, then presents the most recent context-based approaches to NLP for social media. We conclude with an overview of the papers accepted in this special issue, highlighting what we believe are the future directions in processing social media texts.

ANNODIS and Related Projects: Case Studies on the Annotation of Discourse Structure

In this paper we report on the efforts of three projects to annotate texts and dialogues with discourse structure. We provide a theoretical discussion of various alternatives and then present our approach to discourse structure annotation, along with some applications of the resources that we have developed.