Mohamed Ghazouani
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Mohamed Ghazouani has a total of 9 co-authors. Here are the top co-authors by number of shared publications:
- Nadia Chafiq
Hassan II University of Casablanca
3 shared publications - Rokaya El Gounidi
Hassan II University of Casablanca
3 shared publications - Abdellatif Chaouki
CCT College Dublin
2 shared publications - Houyame Lkhider
Purdue University, West Lafayette, IN, USA
1 shared publication - Kamal Moundy
Hassan II University
1 shared publication - Mohamed Akram Lamhour
Hassan II University
1 shared publication
Latest Publications
- 31 January 2026
- Published by Russian State Vocational Pedagogical University in The Education and science journal
- Vol. 28 (2)
The impact of dynamic feedback on AI tutor performance
Introduction . Behavioural adaptive AI systems demonstrate significant potential in providing timely learning support. However, a key aspect of their operation, dynamically switching behavioural patterns based on real-time analysis of streaming data from learners, remains an area requiring further research. Aim . The aim of this study is to assess the impact of a transparent switching policy, based on sentiment and response latency, on student engagement, trust, and academic outcomes, as well as to examine its effect on response latency and expressed sentiment. Methodology and research methods . The authors conducted a randomised, real-world study involving 80 students during a 45-minute session. The experiment compared a dynamic-persona tutor with a fixed-persona baseline tutor. To evaluate the results, the following measures were used: a five-item engagement scale, a five-item trust scale, a curriculum-aligned ten-item pre- and post-knowledge test, log-level tutor-to-learner response latency, and message-level sentiment analysis mapped by a transformer classifier onto a polarity scale ranging from -1 to +1. The role-change algorithm operated as follows: if the rolling mean of sentiment was at or below -0.30, the tutor adopted the role of Empathic Coach; if response latency exceeded ten seconds, the tutor assumed the role of Rational Guide; in all other cases, the tutor remained a Neutral Instructor. Following a role change, there was a one-turn “cooldown” period, and a return to the neutral role occurred after two consecutive stable interactions. Results and scientific novelty . The authors developed a testable role-switching algorithm that selects the optimal interaction strategy in real-time by analysing the learner’s emotional state and response latency. The efficacy of this approach was confirmed in a real-world educational setting. Practical significance . This approach provides a ready-made solution for implementing adaptive learning in real-world educational settings. Its advantages include simple rules, low computational costs, and a transparent auditing system.
- 31 January 2026
- Published by Russian State Vocational Pedagogical University in The Education and science journal
- Vol. 28 (2)
The impact of dynamic feedback on AI tutor performance
Introduction . Behavioural adaptive AI systems demonstrate significant potential in providing timely learning support. However, a key aspect of their operation, dynamically switching behavioural patterns based on real-time analysis of streaming data from learners, remains an area requiring further research. Aim . The aim of this study is to assess the impact of a transparent switching policy, based on sentiment and response latency, on student engagement, trust, and academic outcomes, as well as to examine its effect on response latency and expressed sentiment. Methodology and research methods . The authors conducted a randomised, real-world study involving 80 students during a 45-minute session. The experiment compared a dynamic-persona tutor with a fixed-persona baseline tutor. To evaluate the results, the following measures were used: a five-item engagement scale, a five-item trust scale, a curriculum-aligned ten-item pre- and post-knowledge test, log-level tutor-to-learner response latency, and message-level sentiment analysis mapped by a transformer classifier onto a polarity scale ranging from -1 to +1. The role-change algorithm operated as follows: if the rolling mean of sentiment was at or below -0.30, the tutor adopted the role of Empathic Coach; if response latency exceeded ten seconds, the tutor assumed the role of Rational Guide; in all other cases, the tutor remained a Neutral Instructor. Following a role change, there was a one-turn “cooldown” period, and a return to the neutral role occurred after two consecutive stable interactions. Results and scientific novelty . The authors developed a testable role-switching algorithm that selects the optimal interaction strategy in real-time by analysing the learner’s emotional state and response latency. The efficacy of this approach was confirmed in a real-world educational setting. Practical significance . This approach provides a ready-made solution for implementing adaptive learning in real-world educational settings. Its advantages include simple rules, low computational costs, and a transparent auditing system.
- Open Access
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 120366-120387
Multi-Seed XAI Validation for Reliable LSTM Irrigation Control
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 120366-120387
Open AccessMulti-Seed XAI Validation for Reliable LSTM Irrigation Control
- Open Access
- 20 May 2025
- Published by Salud, Ciencia y Tecnologia in LatIA
- Vol. 3, 315
From Manual Review to AI Automation: An NLP-Powered System for Efficient CV Processing in Academic Admissions
Manual screening of thousands of admissions of master's program applications at Hassan II University of Casablanca is a time and labor-intensive task. Towards this challenge, we designed a machine-based solution utilizing Natural Language Processing (NLP) for summarization and CV ranking on a large set of CVs. Our solution relies on pre-trained spaCy and Hugging Face Transformers-based Named Entity Recognition (NER) models for the retrieval of information such as education, experience, and skills. We then incorporated extractive summarization by using BERT-based models for the selection of the most informative sentences and then the abstractive summarization by utilizing advanced language models such as LLAMA for the summaries to be coherent and easy. We verified our system by conducting a case study of the master's program of Big Data and Data Science by running a set of 2,325 CVs. The model gave very good results like a 72,67 % ROUGE-1 Recall, 74,32 % ROUGE-2 Recall, 73,15 % ROUGE-1 Precision, 57,28 % ROUGE-2 Precision, and 82% Named Entity Recognition (NER) Precision. The system processed a CV on average in 3,84 seconds. We also integrated a conversation bot (chatbot) that allows admissions teams to search the CVs uploaded in real time for improved decision-making effectiveness and significantly decreasing the administrative burden. The promise of NLP-driven automation stands out from this research as a scalable as well as efficient method of screening numerous applicants.
- 20 May 2025
- Published by Salud, Ciencia y Tecnologia in LatIA
- Vol. 3, 315
Open AccessFrom Manual Review to AI Automation: An NLP-Powered System for Efficient CV Processing in Academic Admissions
Manual screening of thousands of admissions of master's program applications at Hassan II University of Casablanca is a time and labor-intensive task. Towards this challenge, we designed a machine-based solution utilizing Natural Language Processing (NLP) for summarization and CV ranking on a large set of CVs. Our solution relies on pre-trained spaCy and Hugging Face Transformers-based Named Entity Recognition (NER) models for the retrieval of information such as education, experience, and skills. We then incorporated extractive summarization by using BERT-based models for the selection of the most informative sentences and then the abstractive summarization by utilizing advanced language models such as LLAMA for the summaries to be coherent and easy. We verified our system by conducting a case study of the master's program of Big Data and Data Science by running a set of 2,325 CVs. The model gave very good results like a 72,67 % ROUGE-1 Recall, 74,32 % ROUGE-2 Recall, 73,15 % ROUGE-1 Precision, 57,28 % ROUGE-2 Precision, and 82% Named Entity Recognition (NER) Precision. The system processed a CV on average in 3,84 seconds. We also integrated a conversation bot (chatbot) that allows admissions teams to search the CVs uploaded in real time for improved decision-making effectiveness and significantly decreasing the administrative burden. The promise of NLP-driven automation stands out from this research as a scalable as well as efficient method of screening numerous applicants.