Other Computer Engineering Commons^™

Bot Detection In Social Media Using Graphsage And Bert, Abhishek Deshmukh

Master's Projects

This project details a novel bot detection system developed to battle the ever- changing challenge of disinformation, misinformation, and other bot-generated content.

The methodology employed in this project combines the text-based analytical strength of BERT (Bidirectional Encoder Representations from Transformers) with the strength of GraphSage (Graph Sample and Aggregation) for analyzing network structures. The project concatenates BERT and GraphSage vectors to create an 896-size feature embedding with a rich blend of network and text features. This project employs a Support Vector Machine to process the concatenated embeddings, as SVM works well with high-dimensional data. This project was evaluated on two …

Analysis And Evaluation Of Different Transformer Architectures For The Protein Sequence Representation And The Corresponding Hypothetical Applications, Mary Mao

Theses and Dissertations

This project is to investigate and assess several Transformer topologies for the modeling of protein sequences and their corresponding uses. Each major model for the protein sequence representations is inspected with its mathematical theory and analyzed for the different performance of the models with various validation repositories.

Stock Price Trend Prediction Using Emotion Analysis Of Financial Headlines With Distilled Llm Model, Rithesh H. Bhat

Computer Science and Engineering Theses - Archive

Capturing the volatility of stock prices helps individual traders, stock analysts, and institutions alike increase their returns in the stock market. Financial news headlines have been shown to have a significant effect on stock price mobility. Lately, many financial portals have restricted web scraping of stock prices and other related financial data of companies from their websites. In this study we demonstrate that emotion analysis of financial news headlines alone can be sufficient in predicting stock price movement, even in the absence of any financial data. We propose an approach that eliminates the need for web scraping of financial data. …

A Two-Stage Machine Learning Approach For Fake News Detection And News Article Categorization, Snegdha Adusumilli

Master's Projects

This project employs machine learning techniques to develop a sequential model for detecting and categorizing fake news, aiming to mitigate its proliferation in today's digital landscape. The model operates in two phases: in the first phase, the classification algorithms like Naïve Bayes, XGBoost and Random Forest are used to distinguish between true and false news stories and in the second phase the capabilities of Naïve Bayes, XGBoost, Random Forest, and the Transformer-based BERT (Bidirectional Encoder Representations from Transformers) model are leveraged to further categorize the news into specific topics.

The methodology encompasses several key steps: data acquisition, preprocessing, feature extraction, …

Ranking-Based Hashtag Recommendation With Collaborative And Content-Based Filtering, Fei Pan

Master's Projects

The purpose of this project is recommending relevant hashtags for users using both Collaborative Filtering (CF) and Content-based filtering with Twitter dataset. The Twitter dataset was collected by leveraging Twitter API v2. After data preprocessing, 40,806 tweets posted by 278 users with 3,107 hashtags from 01/01/2022 to 04/30/2022 are used for model training and testing. For CF models, we will mainly focus on generating embeddings to learn about user and hashtag latent factors and finally predict a probability for unseen hashtags with most possibility will be ranked as topK items for corresponding users. In this project, Matrix Factorization (MF), Neural …

Emotion Detection Using Ensemble Learning, Priya Harika Yerapothu

Master's Projects

Emotion detection is gaining exponential necessity in today’s technological age. This research seeks to delve into ways conversational AI could be enhanced by integrating emotional intelligence using an ensemble learning approach. Traditional machine learning along with advanced neural network architectures are implemented to improve the understanding and intricacies of emotion detection from textual data. The dataset we use is GoEmotions dataset, annotated with 27 emotional labels, to conduct a detailed analysis of emotion recognition. Various machine learning models, such as HistGradientBoosting, LightGBM, CatBoost, and MLP, will be evaluated side by side with advanced models of Bidirectional Long Short-Term Memory (BiLSTM) …

Multimodal Emotion Detection In Conversations And Dialogues: A Fusion Model Approach, Abhinay Jatoth

Master's Projects

Emotion recognition is gaining traction due to its wide range of potential applications across different fields. With the rise of social media, chat platforms, and voice assistants, there is a vast increase in data through which humans implicitly and explicitly carry emotional cues. With new algorithms being developed for understanding the nuances of human language and emotion, businesses can tailor more personalized and empathetic service. Sentiment analysis, expresses a positive, negative, or neutral viewpoint laid the foundation of Emotion classification. Emotion classification in conversations represents the most advanced stage of classification. It is also challenging due to the existence and …

Few-Shot Learning For Ner Using Maml, Nourchene Bargaoui

Theses and Dissertations

This thesis investigates the application of Few-Shot Learning (FSL) using Model-Agnostic Meta-Learning (MAML) to enhance Named Entity Recognition (NER) within the domain of Natural Language Processing (NLP), specifically focusing on chemical datasets. The primary challenge addressed is the impracticality of relying on extensive annotated datasets, especially in specialized fields like chemistry. The research primarily explores the concept of Few-Shot Learning, aiming to train models on minimal data while maintaining performance across diverse tasks. It delves into the N-way K-shot methodology, where "N" represents the number of classes and "K" signifies the number of examples per class. This approach is further …

Automated Medical Notes Labelling And Classification Using Machine Learning, Akhil Prabhakar Thota

Electronic Theses, Projects, and Dissertations

The amount of data generated in medical records, especially in a modern context, is growing significantly. As the amount of data grows, it is very useful to classify the data into relevant classes for further interventions. Different methods that are not automated are very time-consuming and require manual effort have been tried for this before.

Recently deep learning has been used for this task but due to the complexity of the dataset, specifically due to inter-class similarities in the dataset and specific terminology having different meanings in medical contexts has caused significant problems in having a definitive approach to medical …

Bert For Question Answering On Bioasq, Eric R. Fu, Rikel Djoko, Maysam Mansor, Robert Slater

SMU Data Science Review

Machine reading comprehension and question answering are topics of considerable focus in the field of Natural Language Processing (NLP). In recent years, language models like Bidirectional Encoder Representations from Transformers (BERT) [3] have been very successful in language related tasks like question answering. The difficulty of the question answering task lies in developing accurate representations of language and being able to produce answers for questions. In this study, the focus is to investigate how to train and fine tune a BERT model to improve its performance on BioASQ, a challenge on large scale biomedical question answering. Our most accurate BERT …

Eaglebot: A Chatbot Based Multi-Tier Question Answering System For Retrieving Answers From Heterogeneous Sources Using Bert, Muhammad Rana

College of Graduate Studies: Theses & Dissertations

This paper proposes to tackle Question Answering on a specific domain by developing a multi-tier system using three different types of data storage for storing answers. For testing our system on University domain we have used extracted data from Georgia Southern University website. For the task of faster retrieval we have divided our answer data sources into three distinct types and utilized Dialogflow's Natural Language Understanding engine for route selection. We compared different word and sentence embedding techniques for making a semantic question search engine and BERT sentence embedding gave us the best result and for extracting answer from a …