# Classification Benchmarks for Under-resourced Bengali Language based on Multichannel Convolutional-LSTM Network

arXiv: https://arxiv.org/abs/2004.07807 · HTML: https://mlsanity.com/paper/2004.07807/

## Key facts

- Cited by 30 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Apr 2020.

## Built on by (most cited first, 30 of 30)

- [A systematic review of Hate Speech automatic detection using Natural Language Processing](https://mlsanity.com/paper/2106.00742/) (2021)
- [Zero- and Few-Shot Prompting with LLMs: A Comparative Study with Fine-tuned Models for Bangla Sentiment Analysis](https://mlsanity.com/paper/2308.10783/) (2023)
- [BanglaAbuseMeme: A Dataset for Bengali Abusive Meme Classification](https://mlsanity.com/paper/2310.11748/) (2023)
- [Multimodal Hate Speech Detection from Bengali Memes and Texts](https://mlsanity.com/paper/2204.10196/) (2022)
- [BD-SHS: A Benchmark Dataset for Learning to Detect Online Bangla Hate Speech in Different Social Contexts](https://mlsanity.com/paper/2206.00372/) (2022)
- [A Review of Bangla Natural Language Processing Tasks and the Utility of Transformer Models](https://mlsanity.com/paper/2107.03844/) (2021)
- [Offensive Language Identification in Transliterated and Code-Mixed Bangla](https://mlsanity.com/paper/2311.15023/) (2023)
- [BLP-2023 Task 2: Sentiment Analysis](https://mlsanity.com/paper/2310.16183/) (2023)
- [Crosslingual Retrieval Augmented In-context Learning for Bangla](https://mlsanity.com/paper/2311.00587/) (2023)
- [A Comprehensive Study on NLP Data Augmentation for Hate Speech Detection: Legacy Methods, BERT, and LLMs](https://mlsanity.com/paper/2404.00303/) (2024)
- [Interpretable Multi Labeled Bengali Toxic Comments Classification using Deep Learning](https://mlsanity.com/paper/2304.04087/) (2023)
- [Model Adaptation for ASR in low-resource Indian Languages](https://mlsanity.com/paper/2307.07948/) (2023)
- [HS-BAN: A Benchmark Dataset of Social Media Comments for Hate Speech Detection in Bangla](https://mlsanity.com/paper/2112.01902/) (2021)
- [Parameter-Efficient Fine-Tuning for Low-Resource Languages: A Comparative Study of LLMs for Bengali Hate Speech Detection](https://mlsanity.com/paper/2510.16985/) (2025)
- [Authorship Attribution in Bangla Literature (AABL) via Transfer Learning using ULMFiT](https://mlsanity.com/paper/2403.05519/) (2024)
- [A Survey on Automatic Online Hate Speech Detection in Low-Resource Languages](https://mlsanity.com/paper/2411.19017/) (2024)
- [RSM-NLP at BLP-2023 Task 2: Bangla Sentiment Analysis using Weighted and Majority Voted Fine-Tuned Transformers](https://mlsanity.com/paper/2310.14261/) (2023)
- [Milestones in Bengali Sentiment Analysis leveraging Transformer-models: Fundamentals, Challenges and Future Directions](https://mlsanity.com/paper/2401.07847/) (2024)
- [HarmPot: An Annotation Framework for Evaluating Offline Harm Potential of Social Media Text](https://mlsanity.com/paper/2403.11108/) (2024)
- [BanglaEmbed: Efficient Sentence Embedding Models for a Low-Resource Language Using Cross-Lingual Distillation Techniques](https://mlsanity.com/paper/2411.15270/) (2024)
- [Transformer-Based Low-Resource Language Translation: A Study on Standard Bengali to Sylheti](https://mlsanity.com/paper/2510.18898/) (2025)
- [BanglaNirTox: A Large-scale Parallel Corpus for Explainable AI in Bengali Text Detoxification](https://mlsanity.com/paper/2511.01512/) (2025)
- [Bengali Text Classification: An Evaluation of Large Language Model Approaches](https://mlsanity.com/paper/2601.12132/) (2026)
- [Cross-Linguistic Offensive Language Detection: BERT-Based Analysis of Bengali, Assamese, & Bodo Conversational Hateful Content from Social Media](https://mlsanity.com/paper/2312.10528/) (2023)
- [What is the social benefit of hate speech detection research? A Systematic Review](https://mlsanity.com/paper/2409.17467/) (2024)
- [How Effectively Can BERT Models Interpret Context and Detect Bengali Communal Violent Text?](https://mlsanity.com/paper/2506.19831/) (2025)
- [SentiMaithili: A Benchmark Dataset for Sentiment and Reason Generation for the Low-Resource Maithili Language](https://mlsanity.com/paper/2510.22160/) (2025)
- [Gradient Masters at BLP-2025 Task 1: Advancing Low-Resource NLP for Bengali using Ensemble-Based Adversarial Training for Hate Speech Detection](https://mlsanity.com/paper/2511.18324/) (2025)
- [BengaliSent140: A Large-Scale Bengali Binary Sentiment Dataset for Hate and Non-Hate Speech Classification](https://mlsanity.com/paper/2601.20129/) (2026)
- [BnBERT-iPET: Sparse Few-Shot Language Modeling for Bengali via Lottery Ticket Pruning](https://mlsanity.com/paper/2608.05104/) (2026)

## Abstract (arXiv)

Exponential growths of social media and micro-blogging sites not only provide platforms for empowering freedom of expressions and individual voices but also enables people to express anti-social behaviour like online harassment, cyberbullying, and hate speech. Numerous works have been proposed to utilize these data for social and anti-social behaviours analysis, document characterization, and sentiment analysis by predicting the contexts mostly for highly resourced languages such as English. However, there are languages that are under-resources, e.g., South Asian languages like Bengali, Tamil, Assamese, Telugu that lack of computational resources for the NLP tasks. In this paper, we provide several classification benchmarks for Bengali, an under-resourced language. We prepared three datasets of expressing hate, commonly used topics, and opinions for hate speech detection, document classification, and sentiment analysis, respectively. We built the largest Bengali word embedding models to date based on 250 million articles, which we call BengFastText. We perform three different experiments, covering document classification, sentiment analysis, and hate speech detection. We incorporate word embeddings into a Multichannel Convolutional-LSTM (MConv-LSTM) network for predicting different types of hate speech, document classification, and sentiment analysis. Experiments demonstrate that BengFastText can capture the semantics of words from respective contexts correctly. Evaluations against several baseline embedding models, e.g., Word2Vec and GloVe yield up to 92.30%, 82.25%, and 90.45% F1-scores in case of document classification, sentiment analysis, and hate speech detection, respectively during 5-fold cross-validation tests.