Naslov
Text2Emo: Aplikacija za vizualizaciju emocija iz teksta

Autori
Bezić, Dominik

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

Fakultet
Fakultet elektrotehnike i računarstva

Mjesto
Zagreb

Datum
06.07

Godina
2022

Stranica
41

Mentor
Bagić Babac, Marina

Ključne riječi
sentiment analysis ; natural language processing ; CNN ; LSTM ; BERT ; Flutter

Sažetak
Sentiment analysis (or opinion mining) is an approach to natural language processing (NLP) that identifies the emotions behind the text. It is a popular way for businesses to determine and categorize opinions about a product and monitor sentiment in customer feedback and ultimately understand customer needs. This approach involves the use of data mining, machine learning, and artificial intelligence to mine text for sentiment and subjective information. The goal of this thesis is to develop an application for visualizing emotions from the text. The user of the application can enter any kind of text as input and will get a graphical visualization of the distribution of emotions in that text. To achieve this goal, a deep learning model for emotion recognition has to be developed, implemented, and tested.

Izvorni jezik
Engleski

Znanstvena područja
Računarstvo

POVEZANOST RADA