The importance of social media as a way to monitor an electoral campaign is well established. Day-by-day, hour-by-hour evaluation of the evolution of online ideas and opinion allows observers and scholars to monitor trends and momentum in public opinion well before traditional polls. However, there are difficulties in recording and analyzing often brief, unverified comments while the unequal age, gender, social and racial representation among social media users can produce inaccurate forecasts of final polls. Reviewing the different techniques employed using social media to nowcast and forecast elections, this book assesses its achievements and limitations while presenting a new technique of "sentiment analysis" to improve upon them. The authors carry out a meta-analysis of the existing literature to show the conditions under which social media-based electoral forecasts prove most accurate while new case studies from France, the United States and Italy demonstrate how much more accurate "sentiment analysis" can prove.

The importance of social media as a way to monitor an electoral campaign is well established. Day-by-day, hour-by-hour evaluation of the evolution of online ideas and opinion allows observers and scholars to monitor trends and momentum in public opinion well before traditional polls. However, there are difficulties in recording and analyzing often brief, unverified comments while the unequal age, gender, social and racial representation among social media users can produce inaccurate forecasts of final polls. Reviewing the different techniques employed using social media to nowcast and forecast elections, this book assesses its achievements and limitations while presenting a new technique of "sentiment analysis" to improve upon them. The authors carry out a meta-analysis of the existing literature to show the conditions under which social media-based electoral forecasts prove most accurate while new case studies from France, the United States and Italy demonstrate how much more accurate "sentiment analysis" can prove.

Due miliardi e mezzo di utenti internet, oltre un miliardo di account Facebook, 550 milioni di profili Twitter. Che parlano, discutono, si confrontano sui temi piu svariati. Un flusso in continuo divenire di informazioni che da sostanza ogni giorno al mondo dei Big Data. Ma come si analizza concretamente il "sentiment" della Rete? Quali sono i pregi e i limiti dei diversi metodi esistenti? E a quali domande possiamo dare una risposta? Dopo aver presentato le varie tecniche di analisi testuale applicate ai social media, questo libro discute di come l'informazione presente in Rete sia in grado di aiutarci a meglio comprendere il presente e a fare previsioni sul futuro riguardo a una molteplicita di fenomeni sociali, che spaziano dall'andamento dei mercati finanziari, alla diffusione di malattie, alle rivolte e ai sommovimenti popolari fino ai risultati dei talent show, prima di concentrarsi su due casi specifici: l'andamento della felicita degli italiani giorno per giorno, e i risultati delle campagne elettorali in Francia, Stati Uniti e Italia tra il 2012 e il 2013.