Emotion detection in text using machine learning techniques | [Second International Conference on Computing Technologies, Tools and Applications (ICTAPP-24), June 4-6,2024 (Abstract Book) • 2024]

Author(s):

1. Atif Khan: Department of Computer Science, Islamia College Peshawar,KP,Pakistan

2. Fazal Wahid: Department of Computer Science, Islamia College Peshawar,KP,Pakistan

3. Obaid Ajmal: Department of Computer Science, Islamia College Peshawar,KP,Pakistan

4. Farhan Ahmad Awan: Department of Computer Science, Islamia College Peshawar,KP,Pakistan

5. Abrar Ahmed: Department of Computer Science, Islamia College Peshawar, Kp, Pakistan

Abstract:

In recent years, the importance of accurately detecting emotions in text has grown, particularly in the context of business where decision making can be influenced by customer's sentiments. Detecting emotion from text is a complex task and presents unique challenges compared to other modalities like images, videos and audio files, mainly due to the context dependent nature of words. Unlike pictures and audios, text doesn't give obvious clues about emotions which makes it difficult to detect emotions from text. Moreover, the meaning of words can vary depending on their context. Traditional approaches, such as lexicon based or keywords approach tend to have difficulty in recognizing these patterns. In this study, we propose the use of Natural Language Processing (NLP) techniques that are capable of understanding the contextual and semantic meaning of the words. These techniques are combined with both machine learning (ML) and deep learning (DL) algorithms to improve the accuracy of automatic emotion detection. Our experimental results show that DL algorithms outperform the traditional ML algorithms demonstrating their ability in accurately detecting human emotion in text.

Page(s): 1-1

DOI: DOI not available

Published: Journal: Second International Conference on Computing Technologies, Tools and Applications (ICTAPP-24), June 4-6,2024 (Abstract Book), Volume: 0, Issue: 0, Year: 2024

Keywords:

Keywords are not available for this article.

References:

References are not available for this document.

Citations

Citations are not available for this document.

Citations

Downloads

Views