TextNeX: Text Network of eXperts for Robust Text Classification—Case Study on Machine-Generated-Text Detection
Efficient and accurate text classification is essential for a wide range of natural language processing applications, including sentiment analysis, spam detection and machine-generated text identification. While recent advancements in transformer-based large language models have achieved remarkable...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-05-01
|
| Series: | Mathematics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2227-7390/13/10/1555 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850257045948727296 |
|---|---|
| author | Emmanuel Pintelas Athanasios Koursaris Ioannis E. Livieris Vasilis Tampakas |
| author_facet | Emmanuel Pintelas Athanasios Koursaris Ioannis E. Livieris Vasilis Tampakas |
| author_sort | Emmanuel Pintelas |
| collection | DOAJ |
| description | Efficient and accurate text classification is essential for a wide range of natural language processing applications, including sentiment analysis, spam detection and machine-generated text identification. While recent advancements in transformer-based large language models have achieved remarkable performance, they often come with significant computational costs, limiting their applicability in resource-constrained environments. In this work, we propose TextNeX, a new ensemble model that leverages lightweight language models to achieve state-of-the-art performance while maintaining computational efficiency. The development process of TextNeX model follows a three-phase procedure: (i) <i>Expansion</i>: generation of a pool of diverse lightweight models via randomized model setups and variations of training data; (ii) <i>Selection</i>: application of a clustering-based heterogeneity-driven selection to retain the most complementary models and (iii) <i>Ensemble optimization</i>: optimization of the selected models’ contributions using sequential quadratic programming. Experimental evaluations on three challenging text classification datasets demonstrate that TextNeX outperforms existing state-of-the-art ensemble models in accuracy, robustness and computational effectiveness, offering a practical alternative to large-scale models for real-world applications. |
| format | Article |
| id | doaj-art-d60c498f99184c33ac7ab533cd97efaa |
| institution | OA Journals |
| issn | 2227-7390 |
| language | English |
| publishDate | 2025-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Mathematics |
| spelling | doaj-art-d60c498f99184c33ac7ab533cd97efaa2025-08-20T01:56:31ZengMDPI AGMathematics2227-73902025-05-011310155510.3390/math13101555TextNeX: Text Network of eXperts for Robust Text Classification—Case Study on Machine-Generated-Text DetectionEmmanuel Pintelas0Athanasios Koursaris1Ioannis E. Livieris2Vasilis Tampakas3Department of Mathematics, University of Patras, GR 265-00 Patras, GreeceDepartment of Mechanical Engineering and Aeronautics, University of Patras, GR 265-00 Patras, GreeceDepartment of Statistics & Insurance Science, University of Piraeus, GR 185-32 Piraeus, GreeceDepartment of Electrical and Computer Engineering, University of Peloponnese, GR 263-34 Patras, GreeceEfficient and accurate text classification is essential for a wide range of natural language processing applications, including sentiment analysis, spam detection and machine-generated text identification. While recent advancements in transformer-based large language models have achieved remarkable performance, they often come with significant computational costs, limiting their applicability in resource-constrained environments. In this work, we propose TextNeX, a new ensemble model that leverages lightweight language models to achieve state-of-the-art performance while maintaining computational efficiency. The development process of TextNeX model follows a three-phase procedure: (i) <i>Expansion</i>: generation of a pool of diverse lightweight models via randomized model setups and variations of training data; (ii) <i>Selection</i>: application of a clustering-based heterogeneity-driven selection to retain the most complementary models and (iii) <i>Ensemble optimization</i>: optimization of the selected models’ contributions using sequential quadratic programming. Experimental evaluations on three challenging text classification datasets demonstrate that TextNeX outperforms existing state-of-the-art ensemble models in accuracy, robustness and computational effectiveness, offering a practical alternative to large-scale models for real-world applications.https://www.mdpi.com/2227-7390/13/10/1555natural language processingtext classificationlightweight transformer-based modelsmachine-generated text detection |
| spellingShingle | Emmanuel Pintelas Athanasios Koursaris Ioannis E. Livieris Vasilis Tampakas TextNeX: Text Network of eXperts for Robust Text Classification—Case Study on Machine-Generated-Text Detection Mathematics natural language processing text classification lightweight transformer-based models machine-generated text detection |
| title | TextNeX: Text Network of eXperts for Robust Text Classification—Case Study on Machine-Generated-Text Detection |
| title_full | TextNeX: Text Network of eXperts for Robust Text Classification—Case Study on Machine-Generated-Text Detection |
| title_fullStr | TextNeX: Text Network of eXperts for Robust Text Classification—Case Study on Machine-Generated-Text Detection |
| title_full_unstemmed | TextNeX: Text Network of eXperts for Robust Text Classification—Case Study on Machine-Generated-Text Detection |
| title_short | TextNeX: Text Network of eXperts for Robust Text Classification—Case Study on Machine-Generated-Text Detection |
| title_sort | textnex text network of experts for robust text classification case study on machine generated text detection |
| topic | natural language processing text classification lightweight transformer-based models machine-generated text detection |
| url | https://www.mdpi.com/2227-7390/13/10/1555 |
| work_keys_str_mv | AT emmanuelpintelas textnextextnetworkofexpertsforrobusttextclassificationcasestudyonmachinegeneratedtextdetection AT athanasioskoursaris textnextextnetworkofexpertsforrobusttextclassificationcasestudyonmachinegeneratedtextdetection AT ioanniselivieris textnextextnetworkofexpertsforrobusttextclassificationcasestudyonmachinegeneratedtextdetection AT vasilistampakas textnextextnetworkofexpertsforrobusttextclassificationcasestudyonmachinegeneratedtextdetection |