Textual Clues to Stress: A Machine Learning Approach


Notice

This is an unedited manuscript accepted for publication and provided as an Article in Press for early access at the author’s request. The article will undergo copyediting, typesetting, and galley proof review before final publication. Please be aware that errors may be identified during production that could affect the content. All legal disclaimers of the journal apply.

Year : 2025 | Volume : 16 | Issue : 01 | Page : –
    By

    K. Purushotam Naidu,

  • M. Prasanthi,

  • Y. S. P. Kousalya,

  • Trisha Jenna,

  1. Assistant Professor, Department of Computer Science and Engineering (AI & ML), GVP College of Engineering for Women, Visakhapatnam, Andhra Pradesh, India
  2. Student, Department of Computer Science and Engineering (AI & ML), GVP College of Engineering for Women, Visakhapatnam, Andhra Pradesh, India
  3. Student, Department of Computer Science and Engineering (AI & ML), GVP College of Engineering for Women, Visakhapatnam, Andhra Pradesh, India
  4. Student, Department of Computer Science and Engineering (AI & ML), GVP College of Engineering for Women, Visakhapatnam, Andhra Pradesh, India

Abstract

Nowadays, numerous individuals utilize social media platforms to share tweets about their daily lives, which often reflect their mental well-being. Recognizing and managing stress is essential before it becomes a serious issue. Each day, a significant volume of informal messages is posted on discussion forums, blogs, and social networking sites. This study introduces a method for detecting stress using information gathered from social media, with a focus on Twitter. The project encompasses various tasks, including data collection, data cleaning, system training, and stress identification for users. Natural Language Processing (NLP) and Machine learning [ML] methods like SVM, Random Forest [RF], K-Nearest Neighbour [KNN], Naïve Bayes [NB], Decision Tree [DT] will be used to do this. Detecting stress in a timely manner for preventive care is challenging. The proposed study consists of two main components: stress detection through machine learning methods and information extraction through natural language processing. The four primary stages of this study involve text mining, auto summarization, stress detection, and collection of social media data. The suggested model can predict an internet user’s stress level or cognitive load. It incorporates several machine learning strategies, with Support Vector Machine demonstrating superior performance concerning F1 score, accuracy, recall, and precision compared to other methods. The early detection of stress offered by the current methodology will bring significant benefits to society. Therefore, the proposed system utilizes tweets as input to make informed decisions.

Keywords: SVM, Random Forest, K-Nearest Neighbour, Naïve Bayes, Decision Tree, Text Mining, Auto Summarization.

[This article belongs to Journal of Computer Technology & Applications (jocta)]

How to cite this article:
K. Purushotam Naidu, M. Prasanthi, Y. S. P. Kousalya, Trisha Jenna. Textual Clues to Stress: A Machine Learning Approach. Journal of Computer Technology & Applications. 2024; 16(01):-.
How to cite this URL:
K. Purushotam Naidu, M. Prasanthi, Y. S. P. Kousalya, Trisha Jenna. Textual Clues to Stress: A Machine Learning Approach. Journal of Computer Technology & Applications. 2024; 16(01):-. Available from: https://journals.stmjournals.com/jocta/article=2024/view=191752


References

  1. Kumari K, Das S. Stress Detection System using Natural Language Processing and Machine Learning Techniques. InWNLPe-Health@ ICON 2022 (pp. 45-55).
  2. Illahi M, Siddiqui IF, Ali Q, Alvi FA. Ensemble machine learning approach for stress detection in social media texts. Quaid-E-Awam University Research Journal of Engineering, Science & Technology, Nawabshah. 2022;20(02):123-8.
  3. Anakha PS, Devi A, Nair AS, Suresh A, George N. Automated Stress Detection using Machine Learning. International Journal of Engineering Research & Technology (IJERT). 2022;10(04):163-174.
  4. Zubler AV, Yoon JY. Proximal methods for plant stress detection using optical sensors and machine learning. Biosensors. 2020 Nov 29;10(12):193.
  5. V.Acharyulu, N. Sampath Kumar, K.Paavan Sampath, B.Yaswanth Reddy, G. Guna Sekhar. Stress Detection using Machine Learning Technique. Journal of Emerging Technologies and Innovative Research (JETIR). 2023;10(2):e195-e200.
  6. Weerasinghe S, Erfani SM, Alpcan T, Leckie C. Support vector machines resilient against training data integrity attacks. Pattern Recognition. 2019 Dec 1;96:106985.
  7. Reis I, Baron D, Shahaf S. Probabilistic random forest: A machine learning algorithm for noisy data sets. The Astronomical Journal. 2018 Dec 20;157(1):16.
  8. Tabash M, Abd Allah M, Tawfik B. Intrusion detection model using naive bayes and deep learning technique. Int. Arab J. Inf. Technol.. 2020 Mar 1;17(2):215-24.
  9. Bansal M, Goyal A, Choudhary A. A comparative analysis of K-nearest neighbor, genetic, support vector machine, decision tree, and long short term memory algorithms in machine learning. Decision Analytics Journal. 2022 Jun 1;3:100071.
  10. Demirović E, Lukina A, Hebrard E, Chan J, Bailey J, Leckie C, Ramamohanarao K, Stuckey PJ. Murtree: Optimal decision trees via dynamic programming and search. Journal of Machine Learning Research. 2022;23(26):1-47.
Regular Issue Subscription Review Article
Volume 16
Issue 01
Received 05/10/2024
Accepted 12/12/2024
Published 31/12/2024
Visits: 31


Loading citations…