Naslov
Tweet2Sent: Web application for Visualizing Sentiment from Tweets

Autori
Kranjčević, Leon

Vrsta, podvrsta i kategorija rada
Ocjenski radovi, diplomski rad, preddiplomski

Fakultet
Fakultet elektrotehnike i računarstva

Mjesto
Zagreb

Datum
09.07

Godina
2021

Stranica
37

Mentor
Bagić Babac, Marina

Ključne riječi
sentiment analysis ; natural language processing ; stemming ; web scraping ; polarity ; subjectivity ; visualizing

Sažetak
Online social network Twitter allows users to upload short text messages - tweets, and this restriction encourages users to construct focused, timely updates. From the perspective of text analysis, it remains a challenging task to estimate and visualize sentiment for such short and incomplete text snippets. The specific goal of this thesis is to develop a web application for tweet retrieval and visualization that presents sentiment and basic emotional properties embodied in the text. Sentiment from text should be estimated using lexicon-based methods.

Izvorni jezik
Engleski

Znanstvena područja
Računarstvo

POVEZANOST RADA