Sentiment Analysis: An Overview from Linguistics

Abstract

Sentiment analysis is a growing field at the intersection of linguistics and computer science that attempts to automatically determine the sentiment contained in text. Sentiment can be characterized as positive or negative evaluation expressed through language. Common applications of sentiment analysis include the automatic determination of whether a review posted online (of a movie, a book, or a consumer product) is positive or negative toward the item being reviewed. Sentiment analysis is now a common tool in the repertoire of social media analysis carried out by companies, marketers, and political analysts. Research on sentiment analysis extracts information from positive and negative words in text, from the context of those words, and from the linguistic structure of the text. This brief review examines in particular the contributions that linguistic knowledge can make to the task of automatically determining sentiment.

Using lexical level information in discourse structures for Basque sentiment analysis

“…For example, Zhou et al (2011) use discursive in-1 See a detailed review of sentiment analysis in Taboada (2016).…”

Untitled

“…To bridge the gap, there have been attempts to translate some open source English resources into other languages by using the machine translation service. But every language has its peculiarities, which may render the adapting technique unsuitable, so one of the challenges of SA is to create specific linguistic resources for different languages (Balahur et al 2014;Montoyo et al 2012;Ravi & Ravi 2015;Taboada 2016;Zhang et al 2014).…”

“…To help us find a way through this abundance the recent decade has brought a boom in developing automatic text processing systems, which are able to extract, process and present relevant knowledge (Lloret et al 2012). One of these systems is Sentiment Analysis (SA) 1 , whose main goal is to determine whether a text, or a part of it, is subjective or not and, if subjective, whether it expresses a positive or negative view (Taboada 2016). SA has mostly been performed for product reviews (incl.…”

“…Thus, the lexicon has to be adapted to this or that domain. The machinelearning approach requires much human effort in document annotation and a good match between the training and testing data with respect to the domain (Taboada 2016;Zhang et al 2014).…”

Identifying Polarity in Different Text Types

“…To help us find a way through this abundance the recent decade has brought a boom in developing automatic text processing systems, which are able to extract, process and present relevant knowledge (Lloret et al 2012). One of these systems is Sentiment Analysis (SA) 1 , whose main goal is to determine whether a text, or a part of it, is subjective or not and, if subjective, whether it expresses a positive or negative view (Taboada 2016).…”