Sentence-Based Topic Modeling Using Lexical Analysis

Abstract

Data is not meaningful unless its information could be extracted. In every second in this world, we are generating millions of data over the Internet in different form. Most of them are in text format. Usually, data is written based on any topic, or sometimes on few topics. Following this, identifying topic of any text data is very important. Topic identification may help text summarization tools, text classification tool, etc. Machine learning applications may need less training on their data, only if once the topic of text is identified. Therefore, the demand of topic modeling is higher than ever right now. Data scientists are working day and night to make it more effective and accurate using different methods. Topic modeling focuses on the keywords that can express or identify the topic discussed in the document. Topic modeling can save a lot of time by releasing its user from page-to-page manual reviewing. In this paper, a model has been proposed to find out topic of a document. This model works based on the relations between most frequent words and their relation with sentences in the document. This model can be used to increase the accuracy of the topic modeling.