The megaphone of the people? Spanish SentiStrength for real-time analysis of political tweets

Abstract

Twitter is an important platform for sharing opinions about politicians, parties and political decisions. These opinions can be exploited as a source of information to monitor the impact of politics on society. This article analyses the sentiment of 2,704,523 tweets referring to Spanish politicians and parties from a month in 2014–2015. The article makes three specific contributions: (a) enriching SentiStrength, a fast unsupervised sentiment strength detection system, for Spanish political tweeting; (b) analysing how linguistic phenomena such as negation, idioms and character duplication influence Spanish sentiment strength detection accuracy; and (c) analysing Spanish political tweets to rank political leaders, parties and personalities for popularity. Sentiment in Twitter for key politicians broadly reflects the main official polls for popularity but not for voting intention. In addition, the data suggests that the primary role of Twitter in politics is to select and amplify political events published by traditional media.

The rippling dynamics of valenced messages in naturalistic youth chat

“…Second, it has been extended to all six of the languages in our corpus. Of the languages in the corpus, English, Spanish, German, and Russian have had some validation, and French and Portuguese have not been validated (Thelwall et al, 2011;Thelwall et al, 2010;Vilares, Thelwall, & Alonso, 2015). For the two languages that have received the most testing against human raters, English and Spanish, the out-of-thebox SentiStrength ratings tend to have 50% correlation with the judgments of human raters, and we assume comparable correlations for the other languages.…”

On the Processing and Analysis of Microtexts: From Normalization to Semantics

“…Normalization and sentiment analysis might also be useful in higher level text mining applications. Political analysis, where the main goal is to use social media to estimate the popularity of politicians, is of special interest as it can be used as an alternative to traditional polls [8].…”

Language, demographics, emotions, and the structure of online social networks

“…SentiStrength has been shown to perform very closely to human raters in validity tests [41] and has been applied to measure emotions in product reviews [43], online chatrooms [44], Yahoo answers [45], Youtube comments [46], and social media discussions [47]. In addition, SentiStrength allows our approach to be applied in the future to other languages, like Spanish [30,48], and to include contextual factors [49], like sarcasm [50].…”

“…Similar to its English version, the latest adaptation of SentiStrength to Spanish [48] returns values in the range of [1,5] for positive and [-5, -1] for negative sentiment. We ignored neutral tweets that have the combined score of zero (i.e., the same positive and negative scores).…”