Naslov
Sentiment of the Tweets on Russo-Ukrainian War: the Social Network Analysis
(Sentiment of the Tweets on Russo-Ukrainian War: the Social Network Analysis.)

Autori
Poleksić, Andrija ; Martinčić-Ipšić, Sanda

Vrsta, podvrsta i kategorija rada
Radovi u zbornicima skupova, cjeloviti rad (in extenso), znanstveni

Izvornik
46th ICT and Electronics Convention – MIPRO 2023 / Skala, Karolj - Opatija : Hrvatska udruga za informacijsku i komunikacijsku tehnologiju, elektroniku i mikroelektroniku - MIPRO, 2023, 1262-1268

Skup
46th ICT and Electronics Convention – MIPRO 2023

Mjesto i datum
Opatija, Hrvatska, 22.05.2023. - 26.05.2023

Vrsta sudjelovanja
Predavanje

Vrsta recenzije
Međunarodna recenzija

Ključne riječi
Sentiment analysis, Undirected graphs, Community detection, Natural language processing (NLP)

Sažetak
This paper presents the analysis of social network posts using standard natural language processing (NLP) methods and undirected graph representations. The Twitter data used in this work is based on two keywords: Ukraine and Russia in May, October, November and December 2022. After standard pre-processing of the raw data and sentiment classification using "Valence Aware Dictionary and sEntiment Reasoner" (VADER), we proceed to the construction of a weighted and undirected network with hashtags as nodes and hashtag co-occurrences as weighted edges. This representation enables topic extraction based on Louvain community detection. For the quantification of the polarity in the network–community, we propose the "stanciness" metric based on "pnlogratio". The results show that combining sentiment with community structures gives us a deeper insight into the polarity of public opinion on the Russian-Ukrainian war.

Izvorni jezik
Engleski

Znanstvena područja
Računarstvo, Informacijske i komunikacijske znanosti

POVEZANOST RADA