Railway Assistance Chatbot using ANN and NLP
Sajitha Banu1, Narendra Chari2, Lavanya3, Ram Prakash4, Prabhas5.
Department of Artificial Intelligence and Machine Learning, Sasi Institute of Technology and Engineering.
sajithabanu@sasi.ac.in1,narendrachari.kancharla@sasi.ac.in2,lavanya.gubbala@sasi.ac.in3, ramprakash.pemmasani@sasi.ac.in4, prabhas.tunga@sasi.ac.in5.
ABSTRACT- The railway industry serves as a critical transportation network, catering to millions of passengers daily. With increasing demand for efficient and personalized customer support, traditional systems often fail to meet user expectations. This research presents the development of a Railway Enquiry chatbot powered by Artificial Neural Networks (ANN) and Natural Language Toolkit (NLTK), designed to provide an intuitive, efficient, and user-friendly interface for addressing passenger queries. The proposed chatbot leverages NLTK for natural language processing tasks, such as tokenization, stemming, and intent recognition, ensuring accurate understanding of user inputs. ANN is employed for intent classification and response generation, offering a seamless interaction experience. Key functionalities include ticket availability checks, train schedule inquiries, platform details, and fare estimations. The system integrates a preprocessed dataset containing common railwayrelated queries and responses, ensuring comprehensive coverage of user needs. It uses supervised learning techniques to train the ANN model for recognizing intents and providing relevant answers. Evaluation metrics, including accuracy, precision, recall, and F1-score, demonstrate the chatbot's effectiveness in delivering accurate responses. The chatbot is deployed in a web-based interface, enabling users to access railway information conveniently. By automating routine queries, the system reduces dependency on manual customer support and enhances passenger satisfaction. This research highlights the potential of ANN and NLP in revolutionizing customer support systems in the railway sector.
Keywords-Stress Detection, Mental Health, Machine Learning, Deep Learning, Transfer Learning, Chatbot,
Artificial Neural Network (ANN), Stress Management
