Published Paper Details:

The prevalence of people sharing their opinions on social media, Twitter, and restaurant review websites has led to sentiment analysis becoming a popular research topic in natural language processing. Sentiment analysis involves extracting useful information from text data and categorizing it into different labels based on sentiment. This paper discusses the development of supervised machine learning techniques for classifying consumers' words used in their restaurant experiences. The dataset was collected while keeping legal and ethical issues in mind and was preprocessed to prepare it for classification. Supervised machine learning classifiers were then applied to the prepared dataset to build an automated system that classifies text sentiment based on sentence polarity (positive or negative). The paper presents a successful machine learning approach for predicting sentiment (positive or negative) in consumers' restaurant experiences, achieving better accuracy using the Support Vector Machine classifier among other classifiers.