Andrea Ceron

Every tweet counts? How sentiment analysis of social media can improve our knowledge of citizens’ political preferences with an application to Italy and France

The growing usage of social media by a wider audience of citizens sharply increases the possibility of investigating the web as a device to explore and track political preferences. In the present paper we apply a method recently proposed by other social scientists to three different scenarios, by analyzing on one side the online popularity of Italian political leaders throughout 2011, and on the other the voting intention of French Internet users in both the 2012 presidential ballot and the subsequent legislative election. While Internet users are not necessarily representative of the whole population of a country’s citizens, our analysis shows a remarkable ability for social media to forecast electoral results, as well as a noteworthy correlation between social media and the results of traditional mass surveys. We also illustrate that the predictive ability of social media analysis strengthens as the number of citizens expressing their opinion online increases, provided that the citizens act consistently on these opinions.

Using Sentiment Analysis to Monitor Electoral Campaigns: Method Matters-Evidence From the United States and Italy

In recent years, there has been an increasing attention in the literature on the possibility of analyzing social media as a useful complement to traditional off-line polls to monitor an electoral campaign. Some scholars claim that by doing so, we can also produce a forecast of the result. Relying on a proper methodology for sentiment analysis remains a crucial issue in this respect. In this work, we apply the supervised method proposed by Hopkins and King to analyze the voting intention of Twitter users in the United States (for the 2012 Presidential election) and Italy (for the two rounds of the centre-left 2012 primaries). This methodology presents two crucial advantages compared to traditionally employed alternatives: a better interpretation of the texts and more reliable aggregate results. Our analysis shows a remarkable ability of Twitter to “nowcast” as well as to forecast electoral results.

Internet, News, and Political Trust: The Difference Between Social Media and Online Media Outlets

What is the relationship between Internet usage and political trust? To answer this question, we performed a cross-sectional analysis of Eurobarometer survey data related to 27 countries and a supervised sentiment analysis of online political information broadcast during the Italian debate on the reform of public funding of parties. The results disclose the differences between Web 1.0 websites and Web 2.0 social media, showing that consumption of news from information/news websites is positively associated with higher trust, while access to information available on social media is linked with lower trust. This has implications for the debate on social media as a public sphere and for the tension between professional and citizen journalism.

E-campaigning on Twitter: The effectiveness of distributive promises and negative campaign in the 2013 Italian election

Recent studies investigated the effect of e-campaigning on the electoral performance. However, little attention has been paid to the content of e-campaigning. Given that political parties broadcast minute-by-minute the campaign messages on social media, this comprehensive and unmediated information can be useful to evaluate the impact of different electoral strategies. Accordingly, this article examines the electoral campaign for the 2013 Italian general election to assess the effectiveness of positive and negative campaigning messages, measured through content analysis of information published on the official Twitter accounts of Italian parties. We evaluate their impact on the share of unsolicited voting intentions expressed on Twitter, measured through an innovative technique of sentiment analysis. Our results show that negative campaign has positive effects and its impact is stronger when the attacker is meanwhile under attack. Conversely, we only find a circumstantial effect of positive campaign related to clientelistic and distributive appeals.

Brave rebels stay home Assessing the effect of intra-party ideological heterogeneity and party whip on roll-call votes

Sanctions and homogeneity of intra-party preferences are the two main pathways to party unity in roll-call votes. However, only a few works have managed to properly measure the degree of polarization within the party, and therefore the link between ideological preferences and parliamentary voting behaviour has not yet been fully tested. Looking at the internal debates held during party congresses and analysing motions presented by party factions through quantitative text analysis, the present article provides a new measure of intra-party polarization that is exogenous to the parliamentary arena. This measure is used to disentangle the effect of ideological heterogeneity on MPs voting behaviour, net of the party whip. Our results show that factional heterogeneity negatively affects party unity. This effect, however, is conditional on the strength of whipping resources available to the party leader. When the electoral system or the intra-party candidate selection process allows strong discipline to be enforced, the negative effect of heterogeneous preferences on party unity is lower or no longer significant. However, since absences can be a strategy by which to express dissent while avoiding sanctions, they should be considered as an additional voting option and this is crucial to understanding the impact of intra-party heterogeneity on party unity.

The Politics of Fission: An Analysis of Faction Breakaways among Italian Parties (1946–2011)

This article investigates intra-party politics and explores the determinants of factional breakaways, going beyond the unitary actor assumption. It presents a game-theoretic model that focuses on intra-party competition and bargaining dynamics to analyse the interplay between party leaders and minority factions. It tests several hypotheses based on the formal model using a new dataset that contains information about the strength and policy positions of factions inside Italian parties, from 1946 to 2011, measured through quantitative content analysis of motions presented during party congresses. The results show that office, policy and electoral motives influence factions’ decisions to break away. Other elements – such as intra-party democracy, the electoral system and party system competitiveness – also affect leaders’ attitudes toward compromising and alter the likelihood of a split.

iSA: A fast, scalable and accurate algorithm for sentiment analysis of social media content

Abstract We present iSA (integrated sentiment analysis), a novel algorithm designed for social networks and Web 2.0 sphere (Twitter, blogs, etc.) opinion analysis, i.e. developed for the digital environments characterized by abundance of noise compared to the amount of information. Instead of performing an individual classification and then aggregate the predicted values, iSA directly estimates the aggregated distribution of opinions. Based on supervised hand-coding rather than NLP techniques or ontological dictionaries, iSA is a language-agnostic algorithm (based on human coders’ abilities). iSA exploits a dimensionality reduction approach which makes it scalable, fast, memory efficient, stable and statistically accurate. The cross-tabulation of opinions is possible with iSA thanks to its stability. Through empirical analysis it will be shown when iSA outperforms machine learning techniques of individual classification (e.g. SVM, Random Forests, etc) as well as the only other alternative for aggregated sentiment analysis known as ReadMe.

Trust in Government and Media Slant: A Cross-Sectional Analysis of Media Effects in Twenty-Seven European Countries

Several scholars investigate the link between news media and political attitudes of citizens, showing that media exposure affects confidence in political institutions. Beginning from this perspective, we analyze trust in government in twenty-seven European countries, testing the interactive relationship between citizens’ policy views and media slant. Under the assumption that news media bias content in the direction of their audiences or are compliant with potential influence exerted by the government, we use Eurobarometer survey data to measure the effects of the ideological slant of newspapers and public television on trust in government. Our results show that the pro- or antigovernment slant of media outlets interacts with the individual ideological views of each citizen and confirm that media act like “echo-chambers” that reinforce preexisting attitudes. Conversely, the consumption of counter-attitudinal information barely alters trust in government nor does it produce hostile media effects. We also find a slight difference between newspaper readers and public service broadcaster (PSB) users, which seems related to mechanisms of cognitive dissonance.

Intra-party politics in 140 characters

Scholars have emphasized the need to deepen investigation of intraparty politics. Recent studies look at social media as a source of information on the ideological preferences of politicians and political actors. In this regard, the present article tests whether social media messages published by politicians are a suitable source of data. It applies quantitative text analysis to the public statements released by politicians on social media in order to measure intraparty heterogeneity and assess its effects. Three different applications to the Italian case are discussed. Indeed, the content of messages posted online is informative on the ideological preferences of politicians and proved to be useful to understand intraparty dynamics. Intraparty divergences measured through social media analysis explain: (a) a politician’s choice to endorse one or another party leader, (b) a politician’s likelihood to switch off from his or her parliamentary party group; and (c) a politician’s probability to be appointed as a minister.

First- and second-level agenda setting in the Twittersphere: An application to the Italian political debate

ABSTRACT The rise of social network sites reopened the debate on the ability of traditional media to influence public opinion and act as an agenda setter. To answer this question, the present paper investigates first-level and second-level agenda-setting effects in the online environment by focusing on two heated Italian political debates (the reform of public funding of parties and the debate over austerity). By employing innovative and efficient statistical methods such as the lead–lag analysis and supervised sentiment analysis, we compare the attention devoted to each issue and the content spread by online news media and Twitter users. Our results show that online media keep their first-level agenda-setting power even though we find a marked difference between the slant of online news and the Twitter sentiment.