Unveiling Mood Classifications in Malaysia: Analyzing Code-Mixed Twitter Data for Emotional Expression (73814)

Session Information: Communication
Session Chair: Thomas Endres

Friday, 22 September 2023 10:20
Session: Session 1
Room: Gracia
Presentation Type:Oral Presentation

All presentation times are UTC + 2 (Europe/Madrid)

The rapid growth of social media platforms has provided researchers with unprecedented access to user-generated data, enabling the study of public sentiment and mood on a large scale. In a culturally diverse country like Malaysia, it is common to encounter tweets written in various languages, including Malay, Malaysian slang, and English. This linguistic diversity adds complexity to the task of emotion analysis, especially given the limited availability of labeled data necessary for supervised learning techniques. This research paper explores and classifies mood expression among Malaysians, particularly by leveraging code-mixing practices observed on Twitter. The study utilizes the Jupyter Notebook tool to effectively visualize and interpret a dataset comprising 2190 Twitter posts. Emotion classification is performed using the NRCLex Affect dictionary for data analysis and emotion classification. The analysis reveals that approximately 48.3% of Twitter users were likely to express happiness, followed by 21.8% expressing trust, 11.8% expressing fear, 10.8% expressing sadness, 4.5% expressing anger, and 2.8% expressing surprise. The results are promising, as a relatively high accuracy was achieved even with a small initial labeled dataset. This outcome is significant in situations where labeled datasets for emotion analysis are limited. Additionally, the research provides real-time analysis of emotions. The successful classification of mood expression in code-mixed tweets provides insights into Malaysians' emotional states, contributing to a deeper understanding of public sentiment. Understanding the prevailing mood is valuable in gauging public opinion, assessing social trends, and informing decision-making processes at both individual and societal levels.

Latifah Abd Latib, Universiti Selangor, Malaysia
Hema Subramaniam, Universiti Malaya, Malaysia
Affezah Ali, Taylor's University, Malaysia
Siti Khadijah Ramli, Universiti Selangor, Malaysia

About the Presenter(s)
Ts. Dr. Latifah excels as a senior lecturer in Communication & Media, Deputy Dean at Universiti Selangor. A recognized Technologist Specialist by MBOT, she pioneers research, advocates STEM, and promotes literacy through visual communication.

Connect on Linkedin

Connect on ResearchGate

Additional website of interest

See this presentation on the full scheduleFriday Schedule

Conference Comments & Feedback

Place a comment using your LinkedIn profile


Share on activity feed

Powered by WP LinkPress

Share this Presentation

Posted by Clive Staples Lewis

Last updated: 2023-02-23 23:45:00