Other Research Work

This page lists my other research works (NLP and Sensors) done during my graduate and undergraduate studies in Bangladesh. See current research works here.

Natural Language Processing

A Bimodal Longitudinal Investigation on Changes in Sentiments over Social Media Interactions Owing to COVID-19 Pandemic

NLP
Sentiment Analysis
Multimodal
Forecasting
Heuristic
Graduate Work

This study analyzes sentiment shifts on Twitter during the COVID-19 pandemic, revealing significant changes in both text and image sentiment, with negative text sentiment increasing by 10.55% and positive image sentiment decreasing by 24.52%, and introduces a novel bimodal sentiment analysis framework.

December 2025

Impact of Workplace Bullying among Physicians of Tertiary Medical College Hospitals

NLP
Automation
Collaboration

This study examined the prevalence and impact of workplace bullying on stress levels among physicians, finding a significant correlation with symptoms like depression and anxiety. My contribution was developing an automated pipeline to generate Google Forms for efficient survey distribution to 189 physicians, streamlining data collection for the research.

October 2023

An Enhanced RBMT: When RBMT Outperforms Modern Data-Driven Translators

Journal
Collaboration
NLP
Hybrid
Deep Learning
LSTM
Machine Translation
Rule-based

A hybrid approach to machine translation combining both RNN-based and rule-based translators.

February 2022

An Enhanced RBMT: When RBMT Outperforms Modern Data-Driven Translators

Journal
NLP
Hybrid
Deep Learning
LSTM
Machine Translation
Rule-based

I improved Bengali-to-English translation by evaluating rule-based, SMT, and NMT methods and contributing an RNN seq2seq training pipeline for enhanced low-resource translation performance.

March 2021

An Approach Towards Multilingual Translation By Semantic-Based Verb Identification And Root Word Analysis

Machine Translation
NLP
NER

This study explores a generalized machine translation system for low-resource languages like Bengali, proposing semantic-based verb identification and root word detection algorithms that outperform Google Translator, while comparing various approaches in terms of accuracy, time, and space complexity.

December 2018

Polygot: An Approach Towards Reliable Translation By Name Identification And Memory Optimization Using Semantic Analysis

NLP
NER
Rule-based

A rule-based approach for name identification in Bengali Language.

December 2017

A Fault Tolerant Neural Machine Translation System

Fault Tolerant
Machine Translation
NLP
Tensorflow

An effort to improve translation accuracy by combining multiple seq2seq neural machine translation models with augmented training data, completed as part of the CSE6207 project work.

August 2017
No matching items

Sensors and Wireless Networks