UGC Approved Journal no 63975(19)
New UGC Peer-Reviewed Rules

ISSN: 2349-5162 | ESTD Year : 2014
Volume 13 | Issue 2 | February 2026

JETIREXPLORE- Search Thousands of research papers



WhatsApp Contact
Click Here

Published in:

Volume 13 Issue 2
February-2026
eISSN: 2349-5162

UGC and ISSN approved 7.95 impact factor UGC Approved Journal no 63975

7.95 impact factor calculated by Google scholar

Unique Identifier

Published Paper ID:
JETIR2602011


Registration ID:
575289

Page Number

a84-a96

Share This Article


Jetir RMS

Title

An AI-Integrated SBERT-NLP Framework for Job–Internship Recommendation and Interview Question Analysis

Abstract

AI Career Hub is an intelligent job search and career development system that leverages advanced Natural Language Processing to increase the relevance and effectiveness of job recommendations. The platform uses Sentence-BERT embeddings and cosine similarity to overcome the limitations of traditional keyword-based retrieval by tapping into the semantic understanding of job descriptions and candidate profiles. Integrated with real-time job APIs, the system continuously updates job listings while supporting personalized career development through AI-generated interview questions, role-specific preparation, resume analysis, and application tracking. The architecture follows a modular, scalable design, with clear separation of concerns across semantic matching, document parsing, recommendation ranking, and user interaction. Frontend access is provided through a responsive Web interface that provides easy access, while the backend supports secure user management and efficient execution of AI-driven queries. This structure provides both reproducibility for research and adaptability for real-world deployment. Experimental observations reveal that semantic matching with Sentence-BERT improves recommendation relevance and personalized interview preparation raises user engagement and readiness. In summary, AI Career Hub stands out as a holistic and efficient approach to AI-driven career services that integrate semantic retrieval, live job data, and personalized skill development in order to support job seekers in dynamic employment environments.

Key Words

Semantic Matching, Sentence-BERT, Job Recommendation, NLP, AI Career Services, Interview Preparation

Cite This Article

"An AI-Integrated SBERT-NLP Framework for Job–Internship Recommendation and Interview Question Analysis", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.13, Issue 2, page no.a84-a96, February-2026, Available :http://www.jetir.org/papers/JETIR2602011.pdf

ISSN


2349-5162 | Impact Factor 7.95 Calculate by Google Scholar

An International Scholarly Open Access Journal, Peer-Reviewed, Refereed Journal Impact Factor 7.95 Calculate by Google Scholar and Semantic Scholar | AI-Powered Research Tool, Multidisciplinary, Monthly, Multilanguage Journal Indexing in All Major Database & Metadata, Citation Generator

Cite This Article

"An AI-Integrated SBERT-NLP Framework for Job–Internship Recommendation and Interview Question Analysis", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.13, Issue 2, page no. ppa84-a96, February-2026, Available at : http://www.jetir.org/papers/JETIR2602011.pdf

Publication Details

Published Paper ID: JETIR2602011
Registration ID: 575289
Published In: Volume 13 | Issue 2 | Year February-2026
DOI (Digital Object Identifier):
Page No: a84-a96
Country: Bangalore, Karnataka, India .
Area: Engineering
ISSN Number: 2349-5162
Publisher: IJ Publication


Preview This Article


Downlaod

Click here for Article Preview

Download PDF

Downloads

0009

Print This Page

Current Call For Paper

Jetir RMS