Journal of Advanced Research in Computational Linguistics: Journal of Computer Science Language

Unlocking Text Classification Through Supervised Learning Techniques

Chandani — Thu, 26 Mar 2026 00:00:00 +0000

Text classification, a fundamental task in Natural Language Processing (NLP), organises unstructured textual data into predefined categories using supervised learning techniques. This study explores traditional algorithms like Naïve Bayes, Support Vector Machines (SVM), and K-Nearest Neighbours (KNN), alongside advanced deep learning models such as Transformers (e.g., BERT). These methods enhance classification accuracy by leveraging contextual and semantic nuances. The paper addresses challenges like high-dimensional feature spaces, class imbalance, and data scarcity, proposing solutions like feature engineering, Synthetic Minority Oversampling Technique (SMOTE), and transfer learning. Future advancements focus on explainable AI, multilingual capabilities, zero-shot learning, and ethical AI practices to improve scalability, adaptability, and transparency. By integrating traditional and cutting-edge methods, text classification continues to evolve, unlocking applications across domains like sentiment analysis, spam detection, and customer feedback categorisation, driving innovations in NLP and data-driven decision-making.

The Cooperative Relationship Between Artificial Intelligence and Cloud Computing: Transforming Business Activities Efficiently

Parika Jairath — Thu, 22 Jan 2026 00:00:00 +0000

As computer technology has advanced, cloud computing has become a game changer. Both technical and business issues must be resolved for this technology to reach its full potential. The technological issues are the subject of extensive research, but the business consequences are just as important. While AI-driven technology enhances cloud computing research, improving resource management and IT security, cloud computing-specific regulatory issues are also covered, offering policymakers useful information.

The way that IT services are created, implemented, scaled, and maintained has changed dramatically as a result of cloud computing. This modification resolves a significant problem: although the cost of processing power has decreased, many firms still find it difficult and expensive to manage their IT systems. By reducing upfront costs and offering scalable on-demand services, cloud computing aims to close this gap and give businesses access to state-of-the-art IT capabilities.

Cloud computing is a blend of corporate responsiveness with IT efficiency. It enables companies to use compute-intensive analytics, enable mobile engagement, evolve rapidly, and expand applications—all while keeping costs down. Since resources can be intentionally placed in locations with lower energy costs and can also be accessed remotely via the internet, these features remain consistent with the principles of green computing.

Data Acquisition System for Clinical Research in Plethysmographic Signal

Sat, 04 Oct 2025 00:00:00 +0000

Photoplethysmography (PPG) is a non-invasive optical technique used to monitor blood volume changes in peripheral tissues. This paper presents the design and implementation of a low-cost, modular data acquisition (DAQ) system for capturing PPG signals using the MLT1020 sensor. The system includes a custom analogue front end with a bandpass filter (0.5–5 Hz), combining a 5th-order high-pass and 7th-order low-pass filter to suppress noise and motion artefacts. The output signal is visualised in real-time on a Digital Storage Oscilloscope (DSO) and later analysed in MATLAB. Experimental results from human subjects showed clean, periodic waveforms with reliable cardiac cycle representation. Signal quality was comparable to that obtained from commercial DAQ systems, confirming the system’s effectiveness for basic biomedical research. The setup is particularly suited for educational and research settings where cost and customisation are key. Future versions may include microcontroller integration, wireless communication, and digital storage. This system bridges the gap between theory and hands-on experimentation, providing an accessible platform for physiological signal processing.

Exploring the Role of Artificial Intelligence in Personalizing Music Experiences on Spotify

Snehal Shukla, Hiten Darji — Sat, 04 Oct 2025 00:00:00 +0000

This study examines the application of artificial intelligence (AI) in personalising music experiences on Spotify. It analyses the specific AI techniques employed by Spotify, compares these with those used by other major platforms, and highlights Spotify's distinctive innovations. Addressing future directions and challenges in leveraging AI for music personalisation, the study also considers user perspectives, ethical considerations, and potential areas for further research, including bias mitigation and the cold-start problem.

AI-Assisted Child Psychology Platform for Enhancing Emotional and Psychological Well- Being: A Case Study

Lovi Dhamija — Wed, 21 Jan 2026 00:00:00 +0000

Child mental health is an area of growing concern globally, with many children experiencing emotional difficulties such as anxiety, depression, and stress, which often go undiagnosed or untreated. Early intervention and effective emotional support are crucial for the development of healthy coping mechanisms. This paper explores the development and evaluation of an AI-assisted child psychology platform designed to support the emotional well-being of children aged 4-12 years. The platform employs advanced artificial intelligence (AI) to monitor, assess, and provide personalized feedback on children’s emotional states through text, voice, and facial expressions. By utilizing machine learning algorithms, the platform analyzes emotional trends and offers educational tools, coping strategies, and supportive resources tailored to the child’s emotional needs. Furthermore, privacy and ethical considerations are central to the platform’s design. To safeguard sensitive data, the platform incorporates privacy-preserving technologies such as federated learning and differential privacy. Additionally, the system employs bias mitigation strategies to ensure the platform provides equitable emotional support across diverse cultural and linguistic backgrounds. The platform’s effectiveness was evaluated through a pilot study involving 300 children, with results indicating high engagement, improved emotional awareness, and positive behavioral changes. This study demonstrates the potential for AI to enhance mental health support for children in a secure, ethical, and personalized manner, and it provides a blueprint for future developments in the field.

DoI: https://doi.org/10.24321/3051.424X.202403