A Chatbot Intent Classifier for Supporting High School Students

INTRODUCTION: An intent classification is a challenged task in Natural Language Processing (NLP) as we are asking the machine to understand our language by categorizing users’ requests. As result, plays an essential role having chatbot conversation that students’ requests.
 OBJECTIVES: In this study, developed novel called “HSchatbot” for predicting classifications from high school enquiries. Evidently, students schools most concerned among all about their future; thus, stage they need instant support order prepare them take right decision career choice. 
 METHODS: The authors study used Multinomial Naive-Bayes and Random Forest classifiers enquiries, which turn improved performance of using feature’s extractions.
 RESULTS: results show random forest classifier performed better than since model checked different metrics like accuracy, precision, recall F1 score. Moreover, showed accuracy scores exceeding 90% metrics. However, much when CountVectorizers compared TF-IDF.
 CONCLUSION: future work, will be analysed investigated figure out main factors affect classifier, well evaluating with large corpus questions