Luigi Curini

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.

Satisfaction with Democracy and the Winner/Loser Debate: The Role of Policy Preferences and Past Experience

Previous authors have found greater political support among electoral winners than losers, but they define winners and losers at a single time point, and employ a dichotomous categorization that neglects possible variations within each group. This study considers both the past history of winning or losing and the impact of ideological distance from the government on a political support indicator – satisfaction with democracy. Using a multilevel model covering thirty-one countries, the authors show that the relationship between winner/loser status and satisfaction with democracy has a marginal dynamic nature and a policy content. Among present losers, previous experience of victory assuaged dissatisfaction, while among those presenting a consolidated ‘winning’ record, only high ideological proximity to the current government boosted political support.

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.

Missing Links in Party-System Polarization: How Institutions and Voters Matter

This article aims to understand the determinants of party-system polarization by moving beyond the (almost exclusive) emphasis placed in the literature on the role of the electoral system and the number of parties. We propose a larger menu of explanatory variables that includes both institutional and voters-related factors. Regarding the institutional factors, we highlight the consequences of expectations of coalition formations as well as office-related elections (e.g., Presidential ones) on party-system convergence in legislative elections. For the voters-related factors, we address the importance of specific characteristics of the electorate following insights from the spatial theory of voting. To test our hypotheses, we use survey data covering 33 nations and 67 elections. While hypotheses derived from electoral systems and number of parties find little empirical support, the new variables that we consider involving institutions and voters matter significantly.

Experts’ Political Preferences and Their Impact on Ideological Bias An Unfolding Analysis based on a Benoit-Laver Expert Survey

Expert surveys have become increasingly popular among political scientists. One of the problems of using surveys (of any sort) to estimate party positions is that respondents can be influenced by their subjective political views. As a consequence, experts may give biased responses, and such (ideological) bias may affect certain parties more than others. In this paper, we use the latest expert survey of Benoit and Laver (2006) to unfold the ideal points of the respondents to the survey. By employing the estimated ideal points, we show that in almost 16 percent of the cases analyzed, there is evidence of an ideological bias in the experts’ placements of parties along the left—right dimension, especially among right-wing parties (but not necessarily extreme-right parties). We examine two methods designed to generate less biased estimates. The first one is directly based on a regression technique, while the second is based on the negligibility of ideological bias in experts’ answers to more specific policy questions. The paper concludes by examining the consequences of these findings for empirical research.

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.

Government Alternation and Legislative Party Unity: The Case of Italy, 1988–2008

The large literature on legislative party unity identifies the confidence relationship, i.e. the threat of being voted out of office and losing agenda setting powers, as well as cabinet membership, as two crucial institutional sources of party discipline. However, by focusing on the dramatic change in the Italian political system following the 1994 election, the article shows that the impact of these factors on party unity (and the direction of this impact) hinge crucially on the possibility of government alternation rather than mere cabinet turnover. This is illustrated by an index of party unity that explicitly focuses on the behaviour of individual MPs derived from a roll-call analysis of the Italian Chamber of Deputies during the period 1988–2008.

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.

The Conditional Ideological Inducement to Campaign on Character Valence Issues in Multiparty Systems The Case of Corruption

Acknowledging the role played by character valence issues in affecting parties’ fortunes, several recent papers have investigated the possible intentional use of such issues in electoral contests. A corollary of this line of research has focused on identifying conditions under which parties are expected to invest more in valence campaigning. In this article, we focus on the role played by parties’ relative ideological positions in a multiparty setting. We identify the existence of an inverse relationship between the distance of a party from its ideologically adjacent competitors and its incentive to campaign on character valence issues. However, the extent of this relationship can be conditional on institutional and electoral factors. We test these hypotheses by focusing on the emphasis a party places in its electoral manifestos on the specific character valence issue of corruption. Statistical results largely confirm our hypotheses.

A case of valence competition in elections Parties’ emphasis on corruption in electoral manifestos

Despite a growing interest in investigating the causes of political corruption, far less attention has been devoted to analysing the conditions under which political actors have an incentive to highlight corruption in electoral competition. Do parties talk about corruption just as a reaction to exogenous factors (i.e. scandals reported in the press)? Or are there systematic patterns in the way parties emphasize this issue during campaigns? Assuming that corruption is a valence issue (i.e. an issue universally supported/disclaimed by electors), we put our investigation in the framework of a one-dimensional model and hypothesize that spatial considerations can affect parties’ incentives to emphasize corruption issues. Empirical analysis based on CMP data shows that such an incentive exists for both cabinet and non-cabinet parties, and increases with proximity on the ideological scale.