Mariem Ellouze
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Mariem Ellouze has a total of 28 co-authors. Here are the top co-authors by number of shared publications:
- Lamia Hadrich Belguith
University of Sfax
6 shared publications - Asma Mekki
University of Sfax
5 shared publications - Inès Zribi
University of Sfax
3 shared publications - Sami Sayadi
Center for Sustainable Development, College of Arts and Sciences, Qatar University, Doha, Qatar
3 shared publications - Amal Mezghani
University of Sfax
2 shared publications - Rahma Boujelbane
University of Sfax
2 shared publications
Latest Publications
- Open Access
- 14 October 2026
- Published by Elsevier in SSRN Electronic Journal
Quantitative Risk Assessment of spoilage by Bacillus licheniformis of UHT plant-based milk alternatives after a heat treatment
The increasing demand for plant-based milk alternatives requires rigorous quality control to prevent microbial spoilage, particularly from spore-forming bacteria introduced through raw materials. This study develops a Quantitative Microbiological Spoilage Risk Assessment (QMSRA) framework to predict the spoilage risk of plant-based milk alternatives by Bacillus licheniformis.,The physiological lifecycle of B. licheniformis spores, strain CTCPA 3107001, including heat resistance, germination, outgrowth and growth was experimentally characterised and modelled in different media, including a pea-based milk alternative and a clarified derivative. Thermal inactivation kinetics (97.5–105 °C) exhibited non-log-linear behaviour, which was described using the Geeraerd and double Weibull models. Post-treatment recovery kinetics were quantified using flow cytometry and cultural methods. These kinetic parameters were integrated into a five-step QMSRA framework covering the raw material mixing, UHT treatment, aseptic storage, filling, and final product storage and evaluated using Monte Carlo simulations (10,000 iterations).,The results indicate that under typical UHT conditions, the overall spoilage risk is low. However, predictions were highly sensitive to the modeling approach used to describe thermal inactivation, particularly the treatment of resistant spore subpopulations. The Geeraerd model yielded conservative estimates with non-negligible spoilage risk, whereas the double Weibull model predicted negligible spoilage risk. Sensitivity analysis identified raw material contamination, germination capacity and aseptic tank conditions as key drivers. These findings highlight the role of matrix effects and rare resistance spores and underline the importance of accounting for model-related uncertainty in spoilage risk assessment.
- 14 October 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessQuantitative Risk Assessment of spoilage by Bacillus licheniformis of UHT plant-based milk alternatives after a heat treatment
The increasing demand for plant-based milk alternatives requires rigorous quality control to prevent microbial spoilage, particularly from spore-forming bacteria introduced through raw materials. This study develops a Quantitative Microbiological Spoilage Risk Assessment (QMSRA) framework to predict the spoilage risk of plant-based milk alternatives by Bacillus licheniformis.,The physiological lifecycle of B. licheniformis spores, strain CTCPA 3107001, including heat resistance, germination, outgrowth and growth was experimentally characterised and modelled in different media, including a pea-based milk alternative and a clarified derivative. Thermal inactivation kinetics (97.5–105 °C) exhibited non-log-linear behaviour, which was described using the Geeraerd and double Weibull models. Post-treatment recovery kinetics were quantified using flow cytometry and cultural methods. These kinetic parameters were integrated into a five-step QMSRA framework covering the raw material mixing, UHT treatment, aseptic storage, filling, and final product storage and evaluated using Monte Carlo simulations (10,000 iterations).,The results indicate that under typical UHT conditions, the overall spoilage risk is low. However, predictions were highly sensitive to the modeling approach used to describe thermal inactivation, particularly the treatment of resistant spore subpopulations. The Geeraerd model yielded conservative estimates with non-negligible spoilage risk, whereas the double Weibull model predicted negligible spoilage risk. Sensitivity analysis identified raw material contamination, germination capacity and aseptic tank conditions as key drivers. These findings highlight the role of matrix effects and rare resistance spores and underline the importance of accounting for model-related uncertainty in spoilage risk assessment.
- 28 March 2025
- Published by Springer Nature
- p. 183-193
LLMs for Cyberbullying Detection in Political Social Media
- 28 March 2025
- Published by Springer Nature
- p. 183-193
LLMs for Cyberbullying Detection in Political Social Media
- 28 March 2025
- Published by Springer Nature
- p. 91-100
BERT-Based Model for Sarcasm Detection in Arabic Texts
- 28 March 2025
- Published by Springer Nature
- p. 91-100
BERT-Based Model for Sarcasm Detection in Arabic Texts
- 21 March 2024
- Published by Springer Nature
- p. 62-75
Transfer Learning Model for Cyberbullying Detection in Tunisian Social Networks
- 21 March 2024
- Published by Springer Nature
- p. 62-75
Transfer Learning Model for Cyberbullying Detection in Tunisian Social Networks
- Open Access
- 1 January 2024
- Published by Association for Computational Linguistics (ACL)
- p. 788-793
ANLP RG at StanceEval2024: Comparative Evaluation of Stance, Sentiment and Sarcasm Detection
Mezghani Amal, Rahma Boujelbane, Mariem Ellouze. Proceedings of The Second Arabic Natural Language Processing Conference. 2024.
- 1 January 2024
- Published by Association for Computational Linguistics (ACL)
- p. 788-793
Open AccessANLP RG at StanceEval2024: Comparative Evaluation of Stance, Sentiment and Sarcasm Detection
Mezghani Amal, Rahma Boujelbane, Mariem Ellouze. Proceedings of The Second Arabic Natural Language Processing Conference. 2024.
- Open Access
- 20 July 2023
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Asian and Low-Resource Language Information Processing
- Vol. 22 (7) , 1-19
Tokenization of Tunisian Arabic: A Comparison between Three Machine Learning Models
Tokenization represents the way of segmenting a piece of text into smaller units called tokens. Since Arabic is an agglutinating language by nature, this treatment becomes a crucial preprocessing step for many Natural Language Processing (NLP) applications such as morphological analysis, parsing, machine translation, information extraction, and so on. In this article, we investigate word tokenization task with a rewriting process to rewrite the orthography of the stem. For this task, we are using Tunisian Arabic (TA) text. To the best of the researchers’ knowledge, this is the first study that uses TA for word tokenization. Therefore, we start by collecting and preparing various TA corpora from different sources. Then, we present a comparison of three character-based tokenizers based on Conditional Random Fields (CRF), Support Vector Machines (SVM) and Deep Neural Networks (DNN). The best proposed model using CRF achieved an F-measure result of 88.9%.
- 20 July 2023
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Asian and Low-Resource Language Information Processing
- Vol. 22 (7) , 1-19
Open AccessTokenization of Tunisian Arabic: A Comparison between Three Machine Learning Models
Tokenization represents the way of segmenting a piece of text into smaller units called tokens. Since Arabic is an agglutinating language by nature, this treatment becomes a crucial preprocessing step for many Natural Language Processing (NLP) applications such as morphological analysis, parsing, machine translation, information extraction, and so on. In this article, we investigate word tokenization task with a rewriting process to rewrite the orthography of the stem. For this task, we are using Tunisian Arabic (TA) text. To the best of the researchers’ knowledge, this is the first study that uses TA for word tokenization. Therefore, we start by collecting and preparing various TA corpora from different sources. Then, we present a comparison of three character-based tokenizers based on Conditional Random Fields (CRF), Support Vector Machines (SVM) and Deep Neural Networks (DNN). The best proposed model using CRF achieved an F-measure result of 88.9%.
- 26 September 2022
- Published by Springer Nature
- p. 44-51
Sarcasm Detection in Tunisian Social Media Comments: Case of COVID-19
- 26 September 2022
- Published by Springer Nature
- p. 44-51
Sarcasm Detection in Tunisian Social Media Comments: Case of COVID-19
- 24 January 2022
- Published by Springer Nature in Biomass Conversion and Biorefinery
- Vol. 14 (1) , 299-312
Mycoremediation of Tunisian tannery wastewater under non-sterile conditions using Trametes versicolor: live and dead biomasses
- 24 January 2022
- Published by Springer Nature in Biomass Conversion and Biorefinery
- Vol. 14 (1) , 299-312
Mycoremediation of Tunisian tannery wastewater under non-sterile conditions using Trametes versicolor: live and dead biomasses
- Open Access
- 22 September 2021
- Published by Frontiers Media SA in Frontiers in Microbiology
- Vol. 12, 755736
Corrigendum: Modeling Bacillus cereus Growth and Cereulide Formation in Cereal-, Dairy-, Meat-, Vegetable-Based Food and Culture Medium
Corrigendum: Modeling Bacillus cereus Growth and Cereulide Formation in Cereal-, Dairy-, Meat-, Vegetable-Based Food and Culture Medium
- 22 September 2021
- Published by Frontiers Media SA in Frontiers in Microbiology
- Vol. 12, 755736
Open AccessCorrigendum: Modeling Bacillus cereus Growth and Cereulide Formation in Cereal-, Dairy-, Meat-, Vegetable-Based Food and Culture Medium
Corrigendum: Modeling Bacillus cereus Growth and Cereulide Formation in Cereal-, Dairy-, Meat-, Vegetable-Based Food and Culture Medium
- 20 April 2021
- Published by Springer Nature in Language Resources and Evaluation
- Vol. 56 (1) , 357-385
Sentence boundary detection of various forms of Tunisian Arabic
- 20 April 2021
- Published by Springer Nature in Language Resources and Evaluation
- Vol. 56 (1) , 357-385
Sentence boundary detection of various forms of Tunisian Arabic