• Hardik Joshi
• Dr. Hiren Joshi
• Aatithya Hitkar
• Shifa Khan

Author profiling is the task of identifying different personality traits of author by analysing their written text. Different personality traits are author’s gender, age, native language, native city, qualification, occupation etc. Author profiling has different applications such as it could be used in forensics to find the suspect, in marketing, for fake profile identification etc. We aim to predict the author’s age and gender from the multilingual SMS. In this paper we have classify the author gender into male or female categories. Moreover we have classify the author age into three different groups: (i) 15-19, (ii) 20-24, (iii) above 25. Several machine learning classification models like Support Vector Machine, Random Forest, Decision Tree, Naïve Bayes and Linear Regression are used for experiment. Experimental Results show that Support Vector Machine provide better accuracy when used with Count Vectorizer and TFIDF (Term Frequency Inverse Document Frequency).

Multilingual Author Profiling, Natural Language Processing, TFIDF, Support Vector Machine

"MULTILINGUAL AUTHOR PROFILING ON SHORT MESSAGE SERVICE (SMS)", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.5, Issue 6, page no.807-810, June-2018, Available :http://www.jetir.org/papers/JETIR1806920.pdf

"MULTILINGUAL AUTHOR PROFILING ON SHORT MESSAGE SERVICE (SMS)", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.5, Issue 6, page no. pp807-810, June-2018, Available at : http://www.jetir.org/papers/JETIR1806920.pdf