Enhancing Profanity Detection in Textual Data Using Bidirectional Long Short-Term Memory Networks
Kagithala Lakshminadh, Velavolu Sravanthi, K. Koushik, Chavatapalli Surya Bhaskar · 2023
The proliferation of offensive language and content, often referred to as 'profanity,’ poses significant challenges across various digital platforms. Profanity detection in textual data plays a crucial rolein various domains such as social media monitoring, online content moderation, and cyberbullying prevention. This approach aims to enhance profanity detection in textual data using Bidirectional Long Short-Term Memory (BiLSTM) networks to prevent offensive content. The performance of profanity detection is improved in this work by utilizing a novel approach that makes use of cutting-edge deep learning techniques. To be more precise, This approach uses a Bidirectional Long Short-Term Memory network, a powerful deep learning architecture for sequence classification, to model the intricate relationships between words in textual data. Furthermore, this incorporates fine-tuned pre-trained word embeddings to capture semantic information and contextual cues, thereby augmenting the performance of the model. Through extensive experimentation and evaluation of exemplary datasets, the approach achieves a remarkable accuracy rate of 88.3%. Modern methodologies are outperformed by the suggested approach in terms of memory, accuracy, recall, and precision. The efficiency of the method opens up avenues for its application in real-world scenarios, facilitating more effective social media monitoring, online content moderation, and proactive cyberbullying prevention. The findings contribute to advancing the field of profanity detection and hold promise for future research in this domain.