Automatic Language Detection for Low Resource Ho Language

In recent years, social media networking has grown into an amazing improvement in our everyday ways of life. As its popularity grew, more people of all ages began to take advantage of these increasing phenomena. Generally, we convey information or sent text messages to others using different scripts of the language, which is a challenging task to classify the language. Due to the lack of training datasets for low-resource language, it is difficult to detect. In this paper, we have taken Ho language, which is low resource language. The Ho and Odia, both languages are written in the same script i.e. in Odia. The main objective of this paper is to identify Odia and Ho language using different algorithms such as Logistic Regression, Gaussian Naive Bayes, Decision Tree and Random Forest. The paper also states that Precision, Recall, and F-Score were all used as evaluation measures.