Poster
0

Vulgar Remarks Detection in Chittagonian Dialect of Bangla

Avatar
Tanjim Mahmud
Computation and Language
Voices Powered byElevenlabs logo

Authors

Tanjim Mahmud, Michal Ptaszynski, Fumito Masui

Abstract

The negative effects of online bullying and harassment are increasing with Internet popularity, especially in social media. One solution is using natural language processing (NLP) and machine learning (ML) methods for the automatic detection of harmful remarks, but these methods are limited in low-resource languages like the Chittagonian dialect of Bangla.This study focuses on detecting vulgar remarks in social media using supervised ML and deep learning algorithms.Logistic Regression achieved promising accuracy (0.91) while simple RNN with Word2vec and fastTex had lower accuracy (0.84-0.90), highlighting the issue that NN algorithms require more data.

Follow Us on

0 comments

Add comment
Recommended SciCasts
Exploiting Diverse Feature for Multimodal Sentiment Analysis
Avatar
Jia Li16 views
Exploiting Diverse Feature for Multimodal Sentiment Analysis
Time propagation and spectroscopy of Fermionic systems using a stochastic technique
Avatar
Werner Dobrautz101 views
Time propagation and spectroscopy of Fermionic systems using a stochastic technique
Unsupervised Domain Adaptation for Anatomical Landmark Detection
Avatar
Haibo Jin19 views
Unsupervised Domain Adaptation for Anatomical Landmark Detection
Disentangled Ontology Embedding for Zero-shot Learning
Avatar
zhuo-chen30 views
Disentangled Ontology Embedding for Zero-shot Learning
Probabilistic Method of Measuring Linguistic Productivity
Avatar
Sergei Monakhov17 views
Probabilistic Method of Measuring Linguistic Productivity
DictaBERT: A State-of-the-Art BERT Suite for Modern Hebrew
Avatar
Shaltiel Shmidman24 views
DictaBERT: A State-of-the-Art BERT Suite for Modern Hebrew
Augmenting Black-box LLMs with Medical Textbooks for Clinical Question Answering
Avatar
Yubo Wang16 views
Augmenting Black-box LLMs with Medical Textbooks for Clinical Question Answering
Can AI-Generated Text be Reliably Detected?
Avatar
ScienceCast Board 248 views
Can AI-Generated Text be Reliably Detected?
PocketNet: A Smaller Neural Network for Medical Image Analysis
Avatar
aecelaya57 views
PocketNet: A Smaller Neural Network for Medical Image Analysis
WePaMaDM-Outlier Detection: Weighted Outlier Detection using Pattern Approaches for Mass Data Mining
Avatar
Ravindrakumar Purohit93 views
WePaMaDM-Outlier Detection: Weighted Outlier Detection using Pattern Approaches for Mass Data Mining
Variational Information Pursuit with Large Language and Multimodal Models for Interpretable Predictions
Avatar
Kwan Ho Ryan Chan25 views
Variational Information Pursuit with Large Language and Multimodal Models for Interpretable Predictions
Deep quantum neural networks form Gaussian processes
Avatar
marcovsebastian173 views
Deep quantum neural networks form Gaussian processes
MadSGM: Multivariate Anomaly Detection with Score-based Generative Models
Avatar
Haksoo Lim22 views
MadSGM: Multivariate Anomaly Detection with Score-based Generative Models
Panoptic Vision-Language Feature Fields
Avatar
Haoran Chen2 views
Panoptic Vision-Language Feature Fields
Majorana-Magnon Interactions in Topological Shiba Chains
Avatar
Pei-Xin Shen275 views
Majorana-Magnon Interactions in Topological Shiba Chains
Multimodal Contrastive Learning and Tabular Attention for Automated Alzheimer's Disease Prediction
Avatar
Weichen Huang14 views
Multimodal Contrastive Learning and Tabular Attention for Automated Alzheimer's Disease Prediction
Class Prior-Free Positive-Unlabeled Learning with Taylor Variational Loss for Hyperspectral Remote Sensing Imagery
Avatar
Hengwei Zhao13 views
Class Prior-Free Positive-Unlabeled Learning with Taylor Variational Loss for Hyperspectral Remote Sensing Imagery
HOC-Search: Efficient CAD Model and Pose Retrieval from RGB-D Scans
Avatar
Stefan Ainetter3 views
HOC-Search: Efficient CAD Model and Pose Retrieval from RGB-D Scans
Multi-Source Domain Adaptation meets Dataset Distillation through Dataset Dictionary Learning
Avatar
Eduardo Fernandes Montesuma11 views
Multi-Source Domain Adaptation meets Dataset Distillation through Dataset Dictionary Learning
SPOKES: an End-to-End Simulation Facility for Spectroscopic Cosmological Surveys
Avatar
starnord239 views
SPOKES: an End-to-End Simulation Facility for Spectroscopic Cosmological Surveys