Unit:
Κατεύθυνση Ψηφιακά Μέσα Επικοινωνίας και Περιβάλλοντα ΑλληλεπίδρασηςLibrary of the Faculties of Political Science and Public Administration, Communication and Mass Media Studies, Turkish and Modern Asian Studies, Sociology
Supervisors info:
Κωνσταντίνος Μουρλάς, Αναπληρωτής Καθηγητής, Τμήμα Επικοινωνίας και Μέσων Μαζικής Ενημέρωσης, ΕΚΠΑ
Original Title:
Ανάλυση συναισθήματος σε ελληνικά και γερμανικά δεδομένα του Twitter γύρω από την εκπαίδευση των προσφύγων με τη χρήση lexicon- based και machine learning μεθόδων και εργαλείων της γλώσσας R
Translated title:
Sentiment analysis of Greek and German Twitter data regarding the education of refugees using lexicon-based and machine learning methods and tools of the R language
Summary:
The main aim of this thesis is to classify small messages from Twitter (tweets), according to their sentiment, using data mining techniques. In the beginning, the researcher will attempt to detect the opinion targets of the tweets that have to do with the refugee crisis and particularly with the refugees’ education and to categorize them according to their polarity. After that, the sentiment of the above-mentioned tweets is going to be predicted automatically by using two different methods, a lexicon- based, as well as a machine learning method based on the Naive Bayes algorithm.
Main subject category:
Social, Political and Economic sciences
Other subject categories:
Technology - Computer science
Keywords:
refugee crisis, education, sentiment analysis, social media, (un)supervised learning, lexicon, micro-blogging, classifier
Number of references:
139