INTERNATIONAL JOURNAL OF NOVEL RESEARCH AND DEVELOPMENT International Peer Reviewed & Refereed Journals, Open Access Journal ISSN Approved Journal No: 2456-4184 | Impact factor: 8.76 | ESTD Year: 2016
Scholarly open access journals, Peer-reviewed, and Refereed Journals, Impact factor 8.76 (Calculate by google scholar and Semantic Scholar | AI-Powered Research Tool) , Multidisciplinary, Monthly, Indexing in all major database & Metadata, Citation Generator, Digital Object Identifier(DOI)
This research paper introduces a sophisticated data-driven approach for the identification of offensive language on social media, specifically addressing issues related to gender equality and social abuse. In the contemporary landscape, social abuse has become a pressing concern, leading to stress and mental health issues for individuals based on discriminatory thoughts. This study presents a meticulous methodology that begins with the collection and curation of a diverse dataset encompassing personal narratives, news articles, and social media posts, offering a comprehensive perspective on language usage in digital spaces. Through extensive data preprocessing, including sentiment analysis, keyword frequency analysis, and TF-IDF vectorization, the research attains a nuanced understanding of sentiments and concerns surrounding social abuse.
The core of the methodology lies in the application of supervised machine learning algorithms, notably the Support Vector Machine (SVM) model, for the automatic detection of stress-indicating content associated with gender equality. Trained on a labeled dataset, the SVM model exhibits a commendable accuracy of 75 percent in distinguishing offensive from non-offensive tweets. The results contribute valuable insights into the emotional and psychological impact of social abuse, paving the way for targeted interventions and support mechanisms.
Looking ahead, the paper outlines future avenues for exploration, including the incorporation of advanced natural language processing (NLP) techniques and deep learning models to enhance sensitivity. Real-time monitoring and intervention strategies, user feedback integration, and continuous model updating are proposed as areas for future research. The study underscores ethical considerations, emphasizing fairness and impartiality in offensive language detection. In essence, this research forms the basis for advancing the field and invites further exploration into language dynamics, technological advancements, and ethical implications for a more comprehensive contribution to the evolving landscape of digital communication.
Keywords:
natural language processing , Real-time monitoring , Support Vector Machine, TF-IDF vectorization, social abuse, gender equality
Cite Article:
"A Data-Driven Approach to Detect Offensive language in the Context of Social Media Platform", International Journal of Novel Research and Development (www.ijnrd.org), ISSN:2456-4184, Vol.9, Issue 1, page no.b612-b617, January-2024, Available :http://www.ijnrd.org/papers/IJNRD2401170.pdf
Downloads:
000118754
ISSN:
2456-4184 | IMPACT FACTOR: 8.76 Calculated By Google Scholar| ESTD YEAR: 2016
An International Scholarly Open Access Journal, Peer-Reviewed, Refereed Journal Impact Factor 8.76 Calculate by Google Scholar and Semantic Scholar | AI-Powered Research Tool, Multidisciplinary, Monthly, Multilanguage Journal Indexing in All Major Database & Metadata, Citation Generator
Facebook Twitter Instagram LinkedIn