Just Published! iSA: supervised aggregated sentiment analysis of social media

home_cover

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

Information Sciences (Journal IF: 4.038)

Co-authors: Luigi Curini & Stefano M. Iacus

Replication material: www.sciencedirect.com

What is worth remembering:

  • The new algorithm iSA for sentiment/opinion analysis is presented
  • iSA is fast, scalable, accurate and language independent
  • iSA is stable if the number of classes/opinions is large and allows for cross-tabulation
  • iSA works in the case of random and non-random sampling

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.

Just Published! Competing Principals 2.0? Facebook, Renzi and the 2013 Head of State Election

home_cover

Competing Principals 2.0? The impact of Facebook in the 2013 selection of the Italian Head of State

Italian Political Science Review / Rivista Italiana di Scienza Politica

Acknowledgments: Alberto Fragapane and Alessandra Cremonesi for their contribution to data collection. Two anonymous leaders of the former right-wing PD minority faction for providing ‘expert’ information on the factional affiliation of PD MPs.

Replication material: 

andreaceron.com/publications OR http://thedata.harvard.edu/dvn/dv/ipsr-risp

What is worth remembering:

  • Facebook pressure did not affect MPs’ propensity to express public dissent over the party line
  • Contrary to the general wisdom, unexperienced MPs selected through primaries did not conform to social media requests
  • Social media were not (yet) a new ‘competing principals’
  • More traditional ‘principals’ played a role: factional membership, seniority, primary
    elections.
  • ‘Sentimeter’ guys were right
  • It’s not so easy to publish ‘negative’ findings!

Abstract

Motivated by the literature on ‘competing principals’, this article studies the effect of interactive social networking sites on the behavior of politicians. For this purpose, 12,455 comments posted on the Facebook walls of 423 Italian MPs have been analyzed to assess whether Facebook played a role in the selection of the Italian Head of State in 2013, enhancing responsiveness. The statistical analysis reveals that the pressure exerted through social media did not affect MPs’ propensity to express public dissent over the party line, which is instead affected by more traditional ‘principals’ and factors: seniority, primary elections, and factional membership.

Just Published! Social media electoral forecast: State-of-the-art

home_cover

Using Social Media to Forecast Electoral Results: A Review of the State of the Art

Italian Journal of Applied Statistics – Statistica Applicata

Co-authors: Luigi Curini & Stefano M. Iacus

Replication material: andreaceron.com/publications

Acknowledgments: Voices from the Blogs for providing data

What is worth remembering:

  • Many scholars tried to predict elections using social media
  • Some methods are better than others
  • Supervised sentiment analysis seems the best choice
  • Predictions are more accurate in countries with Proportional Representation

Abstract

The paper discusses the advantages of using Supervised Aggregated Sentiment Analysis (SASA) of social media to forecast electoral results and presents an extension of the ReadMe method (Hopkins and King, 2010), which is particularly suitable to addressing a large number of categories (e.g. parties) providing lower standard errors. We analyze the voting intention of social media users in several elections held between 2011 and 2013 in France, Italy, and the United States. We then compare 80 electoral forecasts made using these or other techniques of data-mining and sentiment analysis. The comparison shows that the choice of the method is crucial. Electoral forecasts are also more accurate in countries with higher Internet penetration and given the presence of electoral systems based on proportional representation.

Just Published! Social Media, Flames & Satisfaction with Democracy

home_cover

Flames and Debates: Do Social Media Affect Satisfaction
with Democracy?

Social Indicators Research (Journal IF: 1.395)

Co-author: Vincenzo Memoli

Replication material: andreaceron.com/publications

 

What is worth remembering:

  • Internet usage and consumption of news on Internet are two different things
  • Internet users that consume news from social media are less satisfied with democracy
  • Internet users that consume news from social media are less satisfied with democracy, particularly when they are surrounded by users retaining different views
  • The interactivity of SNS can generate flames!
  • Internet users that consume news from online traditional media are more satisfied with democracy

Abstract

Media plays an important role in defining the quality of democracy in consolidated democracy. Internet, in turn, can wield effects on democracy and many scholars have investigated such relationship. Moving from this literature we use Eurobarometer data to estimate the effect of Internet on the satisfaction with the functioning of democracy among European citizens. The results show that Internet usage, per se, has no effect on the satisfaction with democracy. However, the consumption of online news can make the difference, even though this effect is positive when users consume news from online traditional media while social media has a negative effect, which is mediated by the level of online disagreement and the potential emergence of flames.

Just Published! (Positive and Negative) E-campaigning on Twitter in the 2013 Italian election

home_cover

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

New Media & Society (Journal IF: 2.052)

Co-author: Giovanna d’Adda

Replication material: andreaceron.com/publications

Acknowledgments: Voices from the Blogs; Alessandra Cremonesi; University of Birmingham

What is worth remembering:

  • Analysis of Twitter useful to investigate electoral campaign effects
  • Voting intentions on Twitter react to real events of the campaign
  • Negative campaign effective against rival adjacent parties
  • Negative campaign more effective when the attacker is under attack (voters close ranks!)
  • Negative campaign = more votes for PD (+1.31%) rather than PDL (+0.22%)
  • Distributive promises effective only when properly targeted
  • Distributive promises = more votes for Berlusconi’s PDL (+0.12%) but less for PD (-0.42%)
  • More “Spread” = more votes for Grillo’s M5S (+0.37%) and less for PD (-0.52%)

Abstract

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.