This project is done on Topic modelling(NLP) to understand the concepts of it.
the query is taken from kaggle To build an unsupervised topic model using Latent Dirichlet Allocation (LDA) and build a supervised topic model using term frequency–inverse document frequency (TF-IDF)
I used a corpus of hotel reviews put together by Myle Ott and co-authors. It contains positive and negative hotel reviews. Some are real reviews written by actual customers, while others are fake deceptive reviews. For more details, check out this paper on this dataset:
M. Ott, C. Cardie, and J.T. Hancock. 2013. Negative Deceptive Opinion Spam. In Proceedings of the 2013 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies.
Topic modeling: identifying major themes in a text, usually by identifying informative words. There are two main uses for topic modeling.
-The first is to help in identifying major topics in unlabeled texts.
-The second use is to identify which words are important for text that is labeled for topic.