ISSN :2582-9793

Evaluation of Machine Learning Techniques for Motivational Quotes Classification and Categorization

Original Research (Published On: 30-Sep-2024 )
Evaluation of Machine Learning Techniques for Motivational Quotes Classification and Categorization
DOI : https://dx.doi.org/10.54364/AAIML.2024.43160

Adhiveer Kapuria, Parth Bhavsar and Nishant Kejriwal

Adv. Artif. Intell. Mach. Learn., 4 (3):2746-2763

Adhiveer Kapuria : Pathways School Gurugram

Parth Bhavsar : Defence Institute of Advanced Technology

Nishant Kejriwal : Indian Institute of Technology

Download PDF Here

DOI: https://dx.doi.org/10.54364/AAIML.2024.43160

Article History: Received on: 05-Jul-24, Accepted on: 23-Sep-24, Published on: 30-Sep-24

Corresponding Author: Adhiveer Kapuria

Email: anuj.kapuria@gmail.com

Citation: Adhiveer Kapuria, Parth Bhavsar, Nishant Kejriwal. (2024). Evaluation of Machine Learning Techniques for Motivational Quotes Classification and Categorization. Adv. Artif. Intell. Mach. Learn., 4 (3 ):2746-2763.


Abstract

    

The effective classification and categorization of motivational quotes are critical for various applications in content management and recommendation systems. This paper presents a comprehensive methodology for consolidating and categorizing motivational quotes using machine learning techniques. The dataset, sourced from Kaggle’s Quotes-500K, contains over half a million quotes categorized into various tags such as ”Love,” ”Life,” ”Motivation,” and more. We address category redundancies by consolidating similar tags and selecting appropriate embedding models to capture semantic relationships between quotes. The embedding models are evaluated using t-SNE for finding the most distinctive model for representing motivational quotes. The final categorization focuses on three key cat- egories: ”Love,” ”Inspirational,” and ”Humor”. We then evaluate the performance of several AI models, including Neural Networks, K-Nearest Neighbours (KNN), Euclidean distance-based classifiers, and Cosine Similarity methods. The proposed improved neural network model outperformed other models with a test accuracy of approximately 98%. These results suggest that our approach offers a robust solution for scalable and accurate categorization of motivational content. Future work will explore deeper NLP techniques, fine-tuning strategies for not just increased number of categories but further enhancing the categorization accuracy along with ranking them within their category.

Statistics

   Article View: 51
   PDF Downloaded: 7