Back close

Amrita CEN CIQ: Classification of Insincere Questions

Publication Type : Conference Paper

Publisher : FIRE 2019 - Forum for Information Retrieval Evaluation

Source : FIRE 2019 - Forum for Information Retrieval Evaluation, Kolkata, India (2019)

Url : https://www.researchgate.net/publication/338884744_Amrita_CEN_CIQ_Classification_of_Insincere_Questions

Campus : Coimbatore

School : School of Engineering

Center : Computational Engineering and Networking

Department : Electronics and Communication

Year : 2019

Abstract : This paper explains about the description of the task carried out by the team Amrita CEN CIQ: Classification of Insincere Questions for the shared task conducted by FIRE 2019.The main objective of the shared task taken is to classify the insincere questions into six fine grained classes-Rhetorical questions, Hate speech/ inflammatory questions, Hypothetical questions, Sexually explicit/objectionable content questions, Other and Sincere/ true Information Seeking questions. The proposed system predicts the test data with an accuracy of 48.51%. The classification model used in this task is the Decision Tree Classifier. The Word embedding algorithm used for the extraction of features is Fasttext algorithm. A balanced Decision Tree is used as a classifier and proved to get better results when compared to the Random Forest Classifier with 0.52 F1-score.

Cite this Research Publication : B. Premjith and Dr. Soman K. P., “Amrita CEN CIQ: Classification of Insincere Questions”, in FIRE 2019 - Forum for Information Retrieval Evaluation, Kolkata, India, 2019.

Admissions Apply Now