{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,28]],"date-time":"2026-08-28T05:18:34Z","timestamp":1787894314573,"version":"build-2784847793"},"reference-count":18,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,8,28]],"date-time":"2026-08-28T00:00:00Z","timestamp":1787875200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Big Data"],"abstract":"<jats:sec>\n                    <jats:title>Introduction<\/jats:title>\n                    <jats:p>Part Of Speech (POS) tagging is a fundamental task in Natural Language Processing (NLP) that assigns grammatical labels to words in a sentence. Code mixed text, which entails switching between two or more languages within a single conversation or a sentence, presents challenges for POS tagging. This investigation entailed a comprehensive study of deep learning approaches for cross linguistic POS tagging, focused on English Malayalam code mixed data prevalent on social media platforms. The study was carried out on linguistically complex and varied English Malayalam code mixed text from social media platforms with informal spellings, language switching, transliteration, slang, and unclear grammatical boundaries, reflecting the characteristics of informal online communication. We provide the first structured analysis of micro macro divergence and rare class behavior in English Malayalam code mixed POS tagging.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We evaluated 14 state of the art model configurations that span traditional sequence labeling approaches and multilingual transformer architectures. Models were compared using standard performance metrics prevalent in the domain of data science, supplemented by normalized confusion matrices, error prone tag identification and micro-macro F1 gap analysis.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Our results showed that CRF (No Lang) emerged as the most balanced model overall on macro F1 (all classes) of 0.8170, while (BiLSTM + CRF) achieved the highest macro F1 (seen classes) of 0.8831, precision of 0.9167, and recall of 0.875, though this reflects strong performance concentrated on frequent tag classes rather than balanced coverage across the full tag set. Notably, the pretrained multilingual transformers (mBERT, MuRIL), despite prior exposure to Malayalam during pretraining, were outperformed on several key metrics by CRF and BiLSTM models trained directly on the code mixed dataset.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Discussion<\/jats:title>\n                    <jats:p>This finding was contrary to our expectation that existing multilingual knowledge would translate into a clear advantage on this task and merits further investigation.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fdata.2026.1888885","type":"journal-article","created":{"date-parts":[[2026,8,28]],"date-time":"2026-08-28T04:35:02Z","timestamp":1787891702000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Study of deep learning cues for cross linguistic part of speech tagging in English\u2013 Malayalam code-mixed data"],"prefix":"10.3389","volume":"9","author":[{"given":"Parvathy","family":"Padmakumar","sequence":"first","affiliation":[{"name":"Department of Computer Science and Engineering, Amrita School of Computing, Amrita Vishwa Vidyapeetham, Amritapuri","place":["Kollam, India"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shreya S.","family":"Nair","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Amrita School of Computing, Amrita Vishwa Vidyapeetham, Amritapuri","place":["Kollam, India"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"A. K.","family":"Prajisha","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Amrita School of Computing, Amrita Vishwa Vidyapeetham, Amritapuri","place":["Kollam, India"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"S.","family":"Thara","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Amrita School of Computing, Amrita Vishwa Vidyapeetham, Amritapuri","place":["Kollam, India"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,8,28]]},"reference":[{"key":"B1","article-title":"\u201cPAC-MAN: a synthetic POS-tagged dataset for code-mixed languages,\u201d","volume-title":"Proceedings of the 19th international conference on natural language processing (ICON 2022)","author":"Chatterjee","year":"2022"},{"key":"B2","doi-asserted-by":"publisher","first-page":"8440","DOI":"10.18653\/v1\/2020.acl-main.747","article-title":"\u201cUnsupervised cross-lingual representation learning at scale,\u201d","author":"Conneau","year":"2020","journal-title":"Proceedings of the 58th annual meeting of the association for computational linguistics (ACL 2020)"},{"key":"B3","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1423","article-title":"\u201cBERT: Pre-training of Deep Bidirectional Transformers for Language Understanding,\u201d","author":"Devlin","year":"2019","journal-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1, Minneapolis, Minnesota"},{"key":"B4","article-title":"\u201cLeveraging sub-label dependencies in code-mixed Indian languages for part-of-speech tagging using conditional random fields,\u201d","volume-title":"Proceedings of the WILDRE-6 Workshop, LREC 2020","author":"Gautam","year":"2022"},{"key":"B5","doi-asserted-by":"publisher","first-page":"4021","DOI":"10.1007\/s41870-024-02248-4","article-title":"Efficient text analysis: a BERT-based approach to named entity recognition (NER) and classification for Malayalam language","volume":"17","author":"Gopalakrishnan","year":"2025","journal-title":"Int. J. Inf. Technol"},{"key":"B6","doi-asserted-by":"publisher","first-page":"17","DOI":"10.1007\/978-981-97-4650-7_2","article-title":"\u201cGraphSage-based named entity recognition for malayalam. in intelligent control, robotics, and industrial automation (RCAAI 2023),\u201d","author":"Harikrishnan","year":"2024","journal-title":"Intelligent Control, Robotics, and Industrial Automation: RCAAI 2023, Lecture Notes in Electrical Engineering, Vol. 1220"},{"key":"B7","doi-asserted-by":"publisher","first-page":"3","DOI":"10.19153\/cleiej.29.2.3","article-title":"An empirical comparative study of machine learning, deep learning, and transformer models for text classification","volume":"29","author":"Jain","year":"2026","journal-title":"CLEI Electron. J"},{"key":"B8","article-title":"\u201cTask Report: Tool Contest on POS Tagging for Code-mixed Indian Social Media (Facebook, Twitter, and WhatsApp) Text @ ICON 2016,\u201d","author":"Jamatia","year":"2016","journal-title":"Proceedings of ICON 2016"},{"key":"B9","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/2020.acl-main.329","article-title":"\u201cGLUECoS: an evaluation benchmark for code-switched NLP,\u201d","volume-title":"Proceedings of the 58th annual meeting of the association for computational linguistics (ACL 2020)","author":"Khanuja","year":"2020"},{"key":"B10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-1030","article-title":"\u201cNeural Architectures for Named Entity Recognition,\u201d","author":"Lample","year":"2016","journal-title":"Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, San Diego, California"},{"key":"B11","doi-asserted-by":"publisher","first-page":"329","DOI":"10.32604\/jai.2025.069226","article-title":"Natural language processing with transformer-based models: a meta-analysis","volume":"7","author":"Munyao","year":"2025","journal-title":"J. Artif. Intell"},{"key":"B12","article-title":"\u201cFindings of the shared task on multimodal social media data analysis in Dravidian languages (MSMDA-DL)@DravidianLangTech 2024,\u201d","volume-title":"Proceedings of the 4th workshop on speech, vision, and language technologies for dravidian languages","author":"Premjith","year":"2024"},{"key":"B13","doi-asserted-by":"publisher","first-page":"2876","DOI":"10.1016\/j.procs.2024.04.272.","article-title":"Investigating natural language techniques for accurate noun and verb extraction","volume":"235","author":"Nair","year":"2024","journal-title":"Procedia Comput Sci"},{"key":"B14","article-title":"\u201cUnlocking code-mixed NLP by building resources one language at a time,\u201d","volume-title":"ICON","author":"Sequeira","year":"2015"},{"key":"B15","first-page":"1051","article-title":"\u201cPart-of-Speech Tagging for English-Spanish Code-Switched Text,\u201d","author":"Solorio","year":"2008","journal-title":"Proceedings of the 2008 Conference on Empirical Methods in Natural Language Processing (EMNLP 2008)"},{"key":"B16","doi-asserted-by":"publisher","first-page":"20064","DOI":"10.1109\/ACCESS.2024.3358811","article-title":"Detection of hate speech and offensive language codemix text in Dravidian languages using cost-sensitive learning approach","volume":"12","author":"Sreelakshmi","year":"2024","journal-title":"IEEE Access"},{"key":"B17","doi-asserted-by":"publisher","first-page":"118837","DOI":"10.1109\/ACCESS.2021.3104106","article-title":"Transformer based language identification for Malayalam English code-mixed text","volume":"9","author":"Thara","year":"2021","journal-title":"IEEE Access"},{"key":"B18","doi-asserted-by":"crossref","DOI":"10.3115\/v1\/D14-1105","article-title":"\u201cPOS tagging of English-Hindi code-mixed social media content,\u201d","volume-title":"EMNLP","author":"Vyas","year":"2014"}],"container-title":["Frontiers in Big Data"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fdata.2026.1888885\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,28]],"date-time":"2026-08-28T04:35:27Z","timestamp":1787891727000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fdata.2026.1888885\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,28]]},"references-count":18,"alternative-id":["10.3389\/fdata.2026.1888885"],"URL":"https:\/\/doi.org\/10.3389\/fdata.2026.1888885","relation":{},"ISSN":["2624-909X"],"issn-type":[{"value":"2624-909X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,28]]},"article-number":"1888885"}}