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
Author:
Sinis Dimitrios-Alexandros
Supervisors info:
Κωνσταντίνος Μουρλάς, Αναπληρωτής Καθηγητής, Τμήμα Επικοινωνίας και Μέσων Μαζικής Ενημέρωσης, ΕΚΠΑ
Original Title:
Εύρεση Κανόνων Συγγραφής Δημοσιογραφικών Άρθρων στο Διαδίκτυο με Στόχο την Υψηλή Δημοτικότητα: Η Χρήση Αλγορίθμων Μηχανικής Μάθησης
Translated title:
Finding Rules for Writing Journalistic Articles on the Internet, aiming at High Popularity: The Use of Machine Learning Algorithms
Summary:
The present research studied the popularity of online news articles. More specifically, was created a set of rules, that they can produce news stories with high probability of gaining popularity on the online platform they have posted.
A wide range of news articles features, that came from journalism, marketing, communication and social media fields was investigated in order to uncover them that they lead in high popularity.
The research carried out with the help of innovative practices, such as text mining, natural language processing and Machine Learning algorithms. To implement these practices, was used the Python programming language as well as a multitude of libraries provided by this language.
The results have shown that there are specific combinations of attributes which when obtain specific values, they may give an increased chance of garnering high popularity to the articles that have them.
Main subject category:
Social, Political and Economic sciences
Keywords:
Social Media, Popularity Prediction, Rules of Article Writing, Quality, Machine Learning
