On the usefulness of lexical and syntactic processing in polarity classification of Twitter messages

Abstract

Millions of micro texts are published every day on Twitter. Identifying the sentiment present in them can be helpful for measuring the frame of mind of the public, their satisfaction with respect to a product or their support of a social event. In this context, polarity classification is a subfield of sentiment analysis focussed on determining whether the content of a text is objective or subjective, and in the latter case, if it conveys a positive or a negative opinion. Most polarity detection techniques tend to take into account individual terms in the text and even some degree of linguistic knowledge, but they do not usually consider syntactic relations between words. This article explores how relating lexical, syntactic and psychometric information can be helpful to perform polarity classification on Spanish tweets. We provide an evaluation for both shallow and deep linguistic perspectives. Empirical results show an improved performance of syntactic approaches over pure lexical models when using large training sets to create a classifier, but this tendency is reversed when small training collections are used.

Universal, unsupervised (rule-based), uncovered sentiment analysis

“…Monolingual sentiment analysis systems have been created for languages belonging to a variety of language families, such as Afro-Asiatic (Aldayel and Azmi, Forthcoming), Indo-European (Vilares et al, 2015a;Vilares et al, 2015b;Ghorbel and Jacot, 2011;Scholz and Conrad, 2013;Neri et al, 2012;Habernal et al, 2014;Medagoda et al, 2013;Medagoda et al, 2013), Japonic (Arakawa et al, 2014), Sino-Tibetan (Vinodhini and Chandrasekaran, 2012;Zhang et al, 2009) and Tai-Kadai (Inrak and Sinthupinyo, 2010), among others.…”

Improving Out-of-Domain Sentiment Polarity Classification Using Argumentation

“…We describe the corpus developed for sentence polarity classification in section V-C, as we use this particular corpus for our experiments, summarised in section VI. Twitter has also been a popular subject, with various researchers tackling polarity classification on Tweets [12], [13], [14], [15].…”

Création semi-automatique d’un corpus annoté pour l’analyse d’opinions

“…En outre, des expériences ont montré que les méthodes basées sur les graphes de dépendances peuvent s'avérer nettement meilleures que les approches lexicales [14,26]. Nous avons donc choisi d'augmenter le corpus annoté sémantiquement à partir des caractéristiques syntaxiques des mots impliqués dans les termes annotés.…”