Towards automatic identification of linguistic politeness in Hindi texts
This work addresses the challenge of automated politeness detection in Hindi, a domain-specific task with potential applications in natural language processing for social media or communication analysis, but it is incremental as it applies an existing method (SVM) to new data with feature improvements.
The authors tackled the problem of automatically identifying linguistic politeness in Hindi texts by training an SVM classifier on a manually annotated corpus of over 25,000 blog comments, achieving an accuracy of over 77%, which is within 2% of human accuracy.
In this paper I present a classifier for automatic identification of linguistic politeness in Hindi texts. I have used the manually annotated corpus of over 25,000 blog comments to train an SVM. Making use of the discursive and interactional approaches to politeness the paper gives an exposition of the normative, conventionalised politeness structures of Hindi. It is seen that using these manually recognised structures as features in training the SVM significantly improves the performance of the classifier on the test set. The trained system gives a significantly high accuracy of over 77% which is within 2% of human accuracy.