Topic Detection using Machine Learning IJTSRD



Various types of social media such as blogs, discussion forums and peer-to-peer networks present a wealth of information that can be very helpful. Given vast amount of data, one of the challenge has been to automatically identify the topic of the background chatter. Such emerging topics can be identified by the appearance of multiple posts on a unique subject matter, which is distinct from previous online discourse. We address the problem of identifying topics through the use of machine learning. I propose a topic detection method based on supervised machine learning model, where sentences are labelled, tokenized and the vectorised sentence is trained on densely connected neural network. Compared to conventional gradient descent optimization algorithm, Adam optimizer trains the data much faster and efficiently. Finally the model is tested on an Android App with live data from Google News.

Mr. Ajmal Rasi | Dr. Rajasimha A Makram | Ms. Shilpa Das”Topic Detection using Machine Learning”

Published in International Journal of Trend in Scientific Research and Development (ijtsrd), ISSN: 2456-6470, Volume-2 | Issue-4 , June 2018,

URL: http://www.ijtsrd.com/papers/ijtsrd14272.pdf

http://www.ijtsrd.com/computer-science/artificial-intelligence/14272/topic-detection-using-machine-learning/mr-ajmal-rasi

call for paper Artificial Intelligence, international journal Bioinformatics, ugc approved journals Cognitive Science