Context-Aware Document Summarization System with Risk and Fake Data Detection

K. Bhavadharani; P. Anbumani; S. Dhanavarshini; R. Divyadharshini; S. Dhoolika; C. Dharani

Context-Aware Document Summarization System with Risk and Fake Data Detection

Author(s)	Mrs. K. Bhavadharani, Dr. P. Anbumani, Ms. S. Dhanavarshini, Ms. R. Divyadharshini, Ms. S. Dhoolika, Ms. C. Dharani
Country	India
Abstract	The rapid rise in digital content throughout sectors has prompted a pressing demand for efficient ways of information overload reduction without losing trust and usability. Conventional methods of document summarization focus mainly on single plain text and do not succeed in extracting the entire meaning of multimodal documents that comprise tables, charts, and graphs. In addition, the majority of current methods ignore the dangers posed by privacy-sensitive data, conflicting statements, or made-up content, resulting in summaries that are brief but unreliable. The Context-Aware Document Summarization System with Risk and Fake Data Detection described in this paper produces domain-specific, query-targeted summaries from various forms of documents. The system pre-processes text, tables, and graphs into one representation that encompasses numerical trends and category information along with textual information. Dynamic feature weighting and scoring are used for determining the most informative and relevant sentences while analysing risks and possible disinformation at the same time. Sentences with sensitive, contradictory, or fabricated information are noted and brief explanations are displayed to increase transparency. The proposed solution is applicable to different areas of life, such as healthcare, legal, finance, and news due to the optimization of domain-specific vocabulary and sentence selection fine-tuning based on user queries. This renders the summaries contextually accurate and intent-compliant to the user. Through experimental testing, the system is demonstrated to improve the brevity and relevancy of summaries as well as increase its credibility by identifying risky factors and unreliable data that traditional methods are unable to achieve. Overall, the system brings the intelligent and safer process of summarization, a blend of accuracy, adaptability, and accountability closer.
Keywords	Document Summarization, Context-Aware Systems, Risk Detection, Fake Data Detection, Information Retrieval, Natural Language Processing, Multimodal Summarization, Semantic Embeddings, Domain-Specific Summarization, User Trust, Explainability.
Field	Engineering
Published In	Volume 7, Issue 1, January-February 2026
Published On	2026-01-27

View / Download PDF File

E-ISSN 3048-7641

doi

CrossRef DOI is assigned to each research paper published in our journal.

AIJFR DOI prefix is
10.63363/aijfr

Downloads

Research Paper Format Copyright Permission Form and Undertaking Form Cover Page Vol 7 Isu 1 Cover Page Vol 6 Isu 6 Cover Page Vol 6 Isu 5

All research papers published on this website are licensed under Creative Commons Attribution-ShareAlike 4.0 International License, and all rights belong to their respective authors/researchers.

CC-BY-SA

About AIJFR Fees & Payment Current Issue Publication Archive	Submit Research Paper Track Submission Status Publication Guidelines Publication Ethics Peer Review & Plagiarism	Join as a Reviewer Editors & Reviewers Reviewer Referral Program Get Reviewer Membership Certi.	Website/Journal Policies Usage Policy Content Policies Privacy Policy

Contact Us		+91-9898-79-39-59	editor@aijfr.com

Advanced International Journal for Research

A Widely Indexed Open Access Peer Reviewed Multidisciplinary Bi-monthly Scholarly International Journal

Context-Aware Document Summarization System with Risk and Fake Data Detection

Share this