A new text mining technique has been developed by US researchers. The system works in two stages. Firstly, it uses a statistical tool known as a naive Bayes classifier, a supervised machine-learning algorithm to train for classes. Secondly, it uses k-means analysis, an unsupervised machine-learning algorithm to determine what categories are emerging from the mentions of each class.
The team has tested the efficacy of their data mining tool on updates from the microblogging platform Twitter extracted during the 2016 US presidential elections. The approach allows text mining to work for knowledge discovery, the team suggests. They explain that the approach thus offers a commentary on the current state of the political arena after analysing the candidate tweets and how people are reacting to these tweets.
Malhotra, R. and Malhotra, K. (2018) ‘An analysis of the 2016 US presidential election using Chanakya – a knowledge discovery platform for text mining‘, Int. J. Knowledge Engineering and Data Mining, Vol. 5, Nos. 1/2, pp.17-39.