SACM - United States of America
Permanent URI for this collectionhttps://drepo.sdl.edu.sa/handle/20.500.14154/9668
Browse
3 results
Search Results
Item Restricted ADVANCED LARGE LANGUAGE MODEL APPROACHES AND NATURAL LANGUAGE PROCESSING TECHNIQUES TO IMPROVE HATE SPEECH DETECTION USING AI(University of Central Florida, 2025) Almohaimeed, Saad; Boloni, LadislauThe proliferation of hate speech on social networks can create a significant negative social effect, making the development of AI-based classifiers that can identify and characterize different types of hateful speech in messages highly important for stakeholders. While this is a highly challenging problem, recent advances in language models promise to advance the state of the art such that even subtle and indirect forms of hate speech can be detected. In this dissertation we present a series of contributions that improve different aspects of hate speech classification. We developed THOS, a hate speech dataset consisting of 8.3k tweets. Compared to previous datasets, THOS contains fine-grained labels that identify not only whether a tweet is offensive or hateful, but also the target of the hate. Using this dataset, we studied the degree to which finer grained classification of tweets is feasible. In the follow-up work, we focus on the difficult problem of implicit hate speech, where hate is conveyed through subtle verbal constructs and allusions, without the use of explicitly offensive terms. We evaluate the efficacy of lexicon-based methods, transfer learning, and advanced LLMs such as GPT-4 on this problem. We found that the proposed techniques can boost the detection performance of implicit hate, although even advanced models often struggle with certain interpretations. In our third contribution, we introduce the Closest Positive Cluster (CPC) auxiliary loss, which improves the generalizability of classifiers across a wide range of datasets, resulting in enhanced performance for both explicit and implicit hate speech scenarios. Finally, given the scarcity of implicit hate speech datasets and the abundance of explicit hate datasets, we proposed an approach to generalize explicit hate datasets for the classification of implicit hate speech. Additionally, the proposed approach addresses noisy label correction issues commonly found in crowd-sourced datasets. Our method comprises three key components: influential sample identification, reannotation, and augmentation. We show that the approach improves generalization across datasets and enhances implicit hate classification.15 0Item Restricted Disinformation Classification Using Transformer based Machine Learning(Howard University, 2024) alshaqi, Mohammed Al; Rawat, Danda BThe proliferation of false information via social media has become an increasingly pressing problem. Digital means of communication and social media platforms facilitate the rapid spread of disinformation, which calls for the development of advanced techniques for identifying incorrect information. This dissertation endeavors to devise effective multimodal techniques for identifying fraudulent news, considering the noteworthy influence that deceptive stories have on society. The study proposes and evaluates multiple approaches, starting with a transformer-based model that uses word embeddings for accurate text classification. This model significantly outperforms baseline methods such as hybrid CNN and RNN, achieving higher accuracy. The dissertation also introduces a novel BERT-powered multimodal approach to fake news detection, combining textual data with extracted text from images to improve accuracy. By lever aging the strengths of the BERT-base-uncased model for text processing and integrating it with image text extraction via OCR, this approach calculates a confidence score indicating the likeli hood of news being real or fake. Rigorous training and evaluation show significant improvements in performance compared to state-of-the-art methods. Furthermore, the study explores the complexities of multimodal fake news detection, integrat ing text, images, and videos into a unified framework. By employing BERT for textual analysis and CNN for visual data, the multimodal approach demonstrates superior performance over traditional models in handling multiple media formats. Comprehensive evaluations using datasets such as ISOT and MediaEval 2016 confirm the robustness and adaptability of these methods in combating the spread of fake news. This dissertation contributes valuable insights to fake news detection, highlighting the effec tiveness of transformer-based models, emotion-aware classifiers, and multimodal frameworks. The findings provide robust solutions for detecting misinformation across diverse platforms and data types, offering a path forward for future research in this critical area.34 0Item Restricted Millimeter-Wave Radar Sensing Using Deep Transfer Learning(2023-06) Alkasimi, Ahmad; Pham, Anh-VuMillimeter-wave radar offers several advantages over traditional microwave radar, including higher resolution, greater accuracy, increased sensitivity to small targets, and less atmospheric attenuation. By utilizing deep learning techniques, the raw data can be processed to extract features and classify targets with high accuracy, making it ideal for sensitive applications. This work develops multiple new applications utilizing millimeter-wave FMCW radar. The first application monitors container vibrations to detect drilling vibrations autonomously. The system demonstrates the ability to detect micron-scale intrusive drilling at highway speed for the first time. The second application proposes the use of combined heart sound and gait signals for the first time as biometrics for human identification. Using the image augmentation technique and the joint probability mass function method, the two biometrics are combined to report a 98% identification accuracy. The third application demonstrate the improvement of the radar-based human activity recognition using the combination of four data domains: time-frequency, time-range, range-Doppler and, for the first time, time-angle domain. Six different activities are observed from nine subjects to achieve a combined classification accuracy of 100%. Lastly, the fourth application presents a human tracking system where three classifiers are utilized to identify the subject and their behavior. The system tracks the subject and detect the type of their motion. Based on the detected type of motion, the three classifiers are utilized for identification and activity recognition.12 0