Detecting Emotions from Hindi Text Using Natural Language Processing

With the ever-growing world of user-generated content in local languages, particularly on communication and social media platforms, the need for emotion analysis and interpretation in such content is on the rise. Hindi being one of the biggest global languages provides a complex and rich language structure and uniqueness that calls for emotion classification in a unique way. This paper outlines a method to categorize Hindi text into pre-established emotional classes through Natural Language Processing and Machine Learning methods. The preprocessing process includes language-dependent operations like handling Devanagari script, removing stopwords, normalization, and TF-IDF vectorization. Various machine learning models like Naïve Bayes, Logistic Regression, Extra Trees Classifier, Ridge Classifier, Random Forest Classifier, and Support Vector Classifier was trained and their results were compared using different performance metrics. Performance metrics measured in terms of the following parameters: F1-score, recall, accuracy, precision, false positives, false negatives, true positives, and true negatives. Among the classifiers, Extra Trees Classifier had the maximum accuracy (0.8497). The research proves the efficacy and applicability of machine learning algorithms in analyzing emotional expressions in Hindi language and lays down a basis for sentiment-aware applications in low-resource languages.

• Publication year

  2025

• Venue

  2025 OITS International Conference on Information Technology (OCIT)

• Publication date

  2025-12-18

• Fields of study

  Not labeled

• Identifiers
  DOI 10.1109/OCIT66168.2025.11400138
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Enhanced Patent Classification using Natural Language Processing

  2025cited by this paper
• Estimating the cost of dining for two: An Integration of Sentiment Analysis and Feature Based Approach

  2025cited by this paper
• Am I Hurt?: Evaluating Psychological Pain Detection in Hindi Text Using Transformer-based Models

  2024cited by this paper
• Factors influencing recommendations for women's clothing satisfaction: A latent dirichlet allocation approach using online reviews

  2024cited by this paper
• Weather Forecasting Based Shared Bike Demand Analysis using Machine Learning

  2023cited by this paper
• Sentiment Analysis of Customer Reviews of Food Delivery Services Using Deep Learning and Explainable Artificial Intelligence: Systematic Review

  2022cited by this paper
• EmoInHindi: A Multi-label Emotion and Intensity Annotated Dataset in Hindi for Emotion Recognition in Dialogues

  2022cited by this paper
• End-to-End Federated Learning for Autonomous Driving Vehicles

  2021cited by this paper
• Towards Emotion Recognition in Hindi-English Code-Mixed Data: A Transformer Based Approach

  2021cited by this paper
• Detection of Emotions in Hindi-English Code Mixed Text Data

  2021cited by this paper
• A review on sentiment analysis and emotion detection from text

  2021cited by this paper
• Application of Machine Learning Methods on Patient Reported Outcome Measurements for Predicting Outcomes: A Literature Review

  2021cited by this paper
• Emotion Detection Framework for Twitter Data Using Supervised Classifiers

  2020cited by this paper
• Credit Card Fraud Detection - Machine Learning methods

  2019cited by this paper
• A Study of Tree Based Machine Learning Techniques for Restaurant Reviews

  2018cited by this paper
• Neural Machine Translation by Jointly Learning to Align and Translate

  2014cited by this paper
• Deep Neural Networks for Acoustic Modeling in Speech Recognition: The Shared Views of Four Research Groups

  2012cited by this paper
• Twitter mood predicts the stock market

  2010cited by this paper

• No citing papers are available for this paper.