Amitabha Dey

Amitabha Dey

Lecturer, Computer Science at UNCG | NLP Researcher and Data Scientist

Posts by Collection

portfolio

publications

Fake News Pattern Recognition using Linguistic Analysis

Published in 2018 Joint 7th International Conference on Informatics, Electronics & Vision (ICIEV) and 2018 2nd International Conference on Imaging, Vision & Pattern Recognition (icIVPR), 2018

In the wake of the 2016 US Presidential Election, the upsurge of fake news has been a subject of increased discussion and debate. In this paper, we propose a general framework that can been adopted in future elections worldwide to augment humans in making better decisions when it comes to recognizing news deception and identifying hidden bias of the author. For our study, we constructed a dataset comprising 200 tweets on “Hilary Clinton”, while performing veracity assessment. We initially perform “text normalization” on tweets, explore techniques for feature extraction to classify news into categories, perform a comprehensive linguistic analysis on tweets, extract bag-of-words to find noticeable pattern, and finally apply k-nearest neighbor algorithm for classifying polarized news from credible. We later turn to some popular evaluation metrics to quantify the success rate of our framework, discuss the results of implementing knn algorithm and discuss interconnected research domains and future research directions for constructing an ideal model for fake news detection system around social media.

Recommended citation: A. Dey, R. Z. Rafi, S. Hasan Parash, S. K. Arko and A. Chakrabarty, "Fake News Pattern Recognition using Linguistic Analysis," 2018 Joint 7th International Conference on Informatics, Electronics & Vision (ICIEV) and 2018 2nd International Conference on Imaging, Vision & Pattern Recognition (icIVPR), Kitakyushu, Japan, 2018, pp. 305-309, https://ieeexplore.ieee.org/document/8641018

LDEB – Label Digitization with Emotion Binarization and Machine Learning for Emotion Recognition in Conversational Dialogues

Published in arxiv.org, 2023

Emotion recognition in conversations (ERC) is vital to the advancements of conversational AI and its applications. Therefore, the development of an automated ERC model using the concepts of machine learning (ML) would be beneficial. However, the conversational dialogues present a unique problem where each dialogue depicts nested emotions that entangle the association between the emotional feature descriptors and emotion type (or label). This entanglement that can be multiplied with the presence of data paucity is an obstacle for a ML model. To overcome this problem, we proposed a novel approach called Label Digitization with Emotion Binarization (LDEB) that disentangles the twists by utilizing the text normalization and 7-bit digital encoding techniques and constructs a meaningful feature space for a ML model to be trained. We also utilized the publicly available dataset called the FETA-DailyDialog dataset for feature learning and developed a hierarchical ERC model using random forest (RF) and artificial neural network (ANN) classifiers. Simulations showed that the ANN-based ERC model was able to predict emotion with the best accuracy and precision scores of about 74% and 76%, respectively. Simulations also showed that the ANN-model could reach a training accuracy score of about 98% with 60 epochs. On the other hand, the RF-based ERC model was able to predict emotions with the best accuracy and precision scores of about 78% and 75%, respectively.

Recommended citation: Dey, A., & Suthaharan, S. (2023). LDEB--Label Digitization with Emotion Binarization and Machine Learning for Emotion Recognition in Conversational Dialogues. arXiv preprint arXiv:2306.02193. https://arxiv.org/abs/2306.02193

talks

teaching

CSC 105: Data, Computing, and Quantitative Reasoning

In-person: Fall 2023, Department of Computer Science, UNCG, 2023

This course provides a comprehensive introduction to data analysis using Python, focusing on practical skills and techniques for manipulating, exploring, visualizing, and analyzing data. Through hands-on exercises and real-world examples, students will learn how to leverage popular Python libraries such as Pandas, Matplotlib, Seaborn, and NumPy to extract insights and make data-driven decisions

CSC 250: Foundations of Computer Science I

In-person: Fall 2023, Department of Computer Science, UNCG, 2023

This course introduces fundamental concepts and principles in computer science, equipping students with a strong foundation for further study and practical application in various domains. Topics covered include functions, security, algorithmic paradigms, computational complexity, combinatorics, data structures, compiler design, and automata theory.

CSC 330: Advanced Data Structures

In-person: Spring 2024, Department of Computer Science, UNCG, 2024

This course will delve into an array of advanced topics crucial for mastering data manipulation and algorithmic problem-solving. Topics include static and dynamic arrays, linked lists, hash tables, binary trees, heaps, graphs, and various sorting algorithms. Through comprehensive study and practical implementation, you will gain a deep understanding of these data structures and their associated algorithms, enabling you to analyze their efficiency and apply them effectively to real-world scenarios.

CSC 362: System Programming

In-person: SP24, FA24, SP25, Department of Computer Science, UNCG, 2024

This course will explore key concepts in system-level programming, focusing on the foundational and advanced principles required to build efficient, secure, and robust applications. Topics include terminal commands, Git workflow, C programming fundamentals, dynamic memory allocation, process and memory management, interprocess communication, thread synchronization, and deadlock prevention. Students will also delve into cybersecurity threats, network fundamentals, and virtualization techniques. By mastering these topics through practical implementation and analysis, participants will gain a comprehensive understanding of system programming and its applications in real-world scenarios.