AcademiQ: An AI-Driven Faculty Analytics and Research Publication Summarization System

Abstract

Managing faculty research profiles and academic publications is often a tedious and inconsistent task in aca- demic institutions. Traditional methods of maintaining faculty achievements, publications, and analytics require manual effort, which can lead to delays, inefficiency, and lack of accessibility for students, faculty, and administrators. This project introduces AcademiQ, an AI-driven system de- signed to automatically summarize faculty research publications, analyze academic impact, and provide structured faculty profiles. The system integrates extractive and abstractive summarization techniques (using TextRank and Transformer-based models such as T5/BART), a backend API powered by Flask/Fast API, and a MongoDB database for secure storage and retrieval. On the frontend, AcademiQ offers a faculty list, detailed profiles, a ranking leaderboard, and analytics dashboards for publication trends. Additionally, a feedback module allows stu- dents to provide feedback, which is analyzed using sentiment analysis techniques. The goal of AcademiQ is to make research outputs more accessible, summarized, and comparable, ultimately enhancing faculty visibility, institutional analytics, and decision-making.