Loading article...
Loading article...
Stream/Area:
-
Subject:
-
Paper ID:
IJSREM65490
Volume:
10 |
6 |
Jun 2026
Pages:
1-4
Publication Frequency:
Monthly (12 issues per year)
License:International Journal of Scientific Research in Engineering and Management follows the Creative Commons Attribution 4.0 (CC BY 4.0) License, allowing free use and distribution with proper attribution.
Department of Computer Engineering
ZEAL College of Engineering & Research
Department of Computer Engineering
ZEAL College of Engineering & Research
Department of Computer Engineering
ZEAL College of Engineering & Research
Department of Computer Engineering
ZEAL College of Engineering & Research
Preparing students for modern recruitment processes remains a challenge, as many existing placement preparation methods rely on manual resume reviews, fixed mock interview questions, and limited personalized feedback. To address these shortcomings, this work presents ZTalk-AI, an intelligent placement readiness framework developed to support candidates through automated resume evaluation, adaptive interview practice, behavioral assessment, and readiness scoring. The system employs the Gemini large language model to analyze resume content, generate concise candidate summaries, and suggest suitable job roles based on identified skills and experiences. An adaptive interview module was developed to create role-specific questions whose difficulty changes according to candidate performance during the assessment. To provide a more realistic interview environment, the framework supports both text-based and voice-based interactions using Deepgram speech recognition and Kokoro text-to-speech technologies. During development, particular attention was given to creating an assessment workflow that resembles real recruitment processes while maintaining low response latency and continuous user engagement. In addition to evaluating interview responses, the system incorporates behavioral monitoring features that examine candidate attentiveness and participation throughout interview sessions. A placement readiness score is generated by combining resume quality, interview performance, coding assessment outcomes, and assessment integrity indicators. Experimental observations showed an average resume analysis time of 1.65 seconds and an interview evaluation latency of 1.15 seconds. Candidate-role recommendations demonstrated a correlation accuracy of 94.2% when compared with recruiter evaluations. User feedback collected during testing indicated an average satisfaction rating of 4.6 out of 5, while the proctoring module achieved a precision of 89.5%, recall of 92.1%, and F1-score of 90.8%. The findings suggest that ZTalk-AI can assist both candidates by providing a structured, data-driven approach to placement readiness assessment and interview preparation.
KEYWORDS
The development and evaluation of ZTalk-AI provided valuable insights into the use of artificial intelligence for placement readiness assessment. During testing, it was observed that combining resume analysis, adaptive interviews, behavioral monitoring, and readiness scoring within a single platform offered a broader understanding of candidate performance than isolated assessment methods. The integration of the Gemini Large Language Model enabled automated resume interpretation, role-based question generation, and response evaluation, reducing the dependence on manual assessment processes. The inclusion of Deepgram speech recognition and Kokoro text-to-speech technologies contributed to a more natural interview experience, particularly in voice-based assessment sessions. Feedback collected from participants indicated that adaptive questioning and conversational interactions made interview practice feel closer to actual recruitment scenarios. Behavioral monitoring features also provided useful supplementary information regarding candidate attentiveness and assessment integrity without disrupting the interview flow. From an implementation perspective, the modular architecture proved beneficial for integrating multiple assessment components while maintaining system flexibility and ease of maintenance. Performance results demonstrated that the framework could deliver timely feedback and maintain acceptable response latency even when multiple evaluation processes were executed within the same workflow. Based on the observations obtained during development and testing, the proposed framework shows potential as a practical tool for placement preparation and candidate evaluation. The results suggest that AI-assisted assessment can help candidates identify improvement areas more effectively while providing structured insights that may support recruitment decisions. Future enhancements may include automated skill-gap analysis, semantic job-role matching, predictive placement analytics, and domain-specific model refinement to further improve assessment quality and personalization.
1. B. Bhuvaneswaran, R. Reshma, and V. Soniya, “JobQuench: An Intelligent and Automated Placement Management System for Enhanced Campus Recruitment,” presented at the Proc. of the 3rd Int. Conf. on Augmented Intelligence and Sustainable Systems (ICAISS), 2025, Rajalakshmi Engineering College, Chennai, India. 2. P. S. Prakash, K. Siranjeevi, N. Vinoth Kumar, G. Pathmesh, and A. Ponnarasu, “NexInterview – AI-Driven Mock Interview Preparation Platform,” International Journal of Advanced Research in Science, Communication and Technology (IJARSCT), vol. 5, no. 7, pp. 279–288, May 2025. 3. A. Halle et al., “Training and Placement Management System,” International Journal for Research in Engineering Application Management (IJREAM), 2025. 4. S. R. Jagtap, V. Kulkarni, Y. Pachorkar, O. Taur, S. Gupta, and U. Pujeri, “AI-Driven Real-Time Interview Simulation App with Voice Recognition and Facial Analysis,” Indian Journal of Science and Technology, vol. 18, no. 25, pp. 2058–2066, Jul. 2025. 5. N. Chavan, P. Shivpuje, S. Mali, and A. Sayyad, “AI Based Mock Interview System,” International Research Journal of Modernization in Engineering Technology and Science (IRJMETS), vol. 6, no. 10, Oct. 2024. 6. P. Padwal et al., “E-Training and Placement Management System,” International Research Journal of Computer and Communication Engineering, 2022. 7. P. Chavan and S. Jadhav, “A General Paper on AI Based Mock Interview System,” International Journal of Scientific Research in Science, Engineering and Technology (IJSRSET), vol. 13, no. 1, pp. 118–126, Jan.–Feb. 2026. 8. S. Khale, M. Grover, and S. Kadam, “A Dynamic, Full Featured Portal for Campus Placement,” International Journal of Research in Engineering, Science and Management, 2024. 9. A. Nanotkar, N. Jamgade, P. Tiwari, and S. Ninawe, “Development of Web Application to Automate Training Placement Process,” International Journal of Novel Research and Development, 2023. 10. K. Mahalakshmi and R. Sathish Kumar, “Online Placement Cell Management System,” International Journal of Research Publication and Reviews, 2024. 11. Google DeepMind, “Gemini: A Family of Highly Capable Multimodal Models,” 2024.
Publication Date
6/25/2026
Peer Review Type
Double-Blind Peer Review
Review Rounds: 2
Documents
Article Views
0
Total views since publication
PDF Downloads
4
Total downloads since publication
Geographic Reach
5
Digital Preservation: This article is permanently archived on Zenodo and complies with all data preservation standards across major indexing platforms.
Plagiarism Screening
This manuscript has been checked for plagiarism using TurnitinPlagiarismChecker software.
Conflict of Interest
The authors declare no conflict of interest related to this research work.
Funding Information
No funding information available for this research.
Related research in the same subject area
Loading similar articles...