Growing migration flows towards and within Europe lead to various emotional reactions within the societies of European countries and the general attitude towards immigrants is an often discussed topic in politics. The question of how European societies perceive immigrants, is approached by a Sentiment Analysis in four languages, which are spoken in Europe. The necessary data was collected from Twitter over the period of one month. After classifying, training and testing a considerable amount of Tweets for each language, it should be possible to derive general tendencies of sentiments towards migration within a society. In order to set the results into a brought perspective, the results are finally compared to other migration data in the corresponding countries.
Il costante e attuale aumento dei flussi migratori verso l’Europa e all’interno della stessa comporta svariate reazioni emotive negli stati europei e il relativo atteggiamento nei confronti degli immigrati è un argomento di estrema rilevanza. In questa tesi si affronta il tema della percezione degli immigrati in Europa attraverso lo strumento statistic-linguistico della ‘sentiment analysis’ effettuata in 4 lingue differenti: italiano, inlgese, francese e Tedesco. Sono stati raccolti dati twitter nel corso di un mese del 2015 e si è proceduta alla raccolta ripulitura e classificazione di un ingente numero di tweet per ciascuna lingua, al fine di individuare il sentimento prevalente nei confronti del tema dell’immigrazione. Tali risultati sono stati altresì confrontati con statistiche ufficiali sull’immigrazione per ciascuno stato.
Migration in Europe – A Sentiment Analysis of Twitter Data
STOLZ, LISA
2014/2015
Abstract
Growing migration flows towards and within Europe lead to various emotional reactions within the societies of European countries and the general attitude towards immigrants is an often discussed topic in politics. The question of how European societies perceive immigrants, is approached by a Sentiment Analysis in four languages, which are spoken in Europe. The necessary data was collected from Twitter over the period of one month. After classifying, training and testing a considerable amount of Tweets for each language, it should be possible to derive general tendencies of sentiments towards migration within a society. In order to set the results into a brought perspective, the results are finally compared to other migration data in the corresponding countries.È consentito all'utente scaricare e condividere i documenti disponibili a testo pieno in UNITESI UNIPV nel rispetto della licenza Creative Commons del tipo CC BY NC ND.
Per maggiori informazioni e per verifiche sull'eventuale disponibilità del file scrivere a: unitesi@unipv.it.
https://hdl.handle.net/20.500.14239/9897