Mahshad Haghi - Department of Industrial & Systems Engineering, Tarbiat Modares University, Tehran, Iran

Nowadays, there is an abundance of textual data available for analysis. Common applications of text analysis include sentiment analysis of user comments and differentiating between legitimate and spam emails. However, text mining for extracting insights from novels remains relatively rare. Since novels represent valuable resources, simplifying the process of comprehending novels can offer significant benefits. This paper focuses on the text of the renowned novel called "Anne of Green Gables". A variety of machine learning algorithms, including natural language processing techniques, are applied to discover valuable insights from the text. Our analysis encompasses identifying the most frequently occurring words and their associated parts of speech in this novel, utilizing Named Entity Recognition (NER) to detect proper nouns, employing data visualization to enhance understanding, and extracting a summary of the part of this novel. This study showcases the informative potential of employing machine learning techniques in the analysis of literary works.

Text mining, Machine learning, Natural language processing (NLP), Visualization