Research Article Volume - 8 Issue - April 2018 DOI: 10.19080/JFSCI.2018.08.555733 J Forensic Sci & Criminal Inves Copyright © All rights are reserved by Pooja Ahuja Authorship Profiling of Instant Messaging Sites based on Stylistic and Stylometric Analysis Gloria Christal 1 , Prajakta Manve 1 , Pooja Ahuja* 2 and MS Dahiya 3 1Student, MSc. Forensic science, Institute of Forensic Science, Gujarat Forensic Sciences University, India 2Assistant professor, Institute of Forensic Science, Gujarat Forensic Sciences University, India 3Director, Institute of Forensic Science, Gujarat Forensic Sciences University, India Submission: March 16, 2018; Published: April 04, 2018 *Corresponding author: Pooja Ahuja, Assistant professor, Institute of Forensic Science, Gujarat Forensic Sciences University, India, Email: J Forensic Sci & Criminal Inves 8(2): JFSCI.MS.ID.555733 (2018) 001 Introduction The increase in popularity of the Internet media, like emails, blogs/internet forum and websites have been identified as the ideal communication platform for people and one such medium is Instant Messaging (IM) which has gained prominence recently with rise of the Internet. Instant messaging is a type of online chat that offers real-time text transmission over the Internet. The Global Web Index report was conducted across 32 markets involving 170,000 internet users. The study shows that 52 per cent of Indian instant messaging users are on WhatsApp, while 42 per cent use Facebook Messenger, 37 per cent use Skype, We Chat has a 26 per cent share in the market and Viber with 18 per cent market share is in the fifth spot IM is a set of communication technologies used for text-based communication between two or more participants over the Internet or other types of networks instantly [1]. Forensic linguistics, legal linguistics, or language and the law, is the application of linguistic knowledge, methods and insights to the forensic context of law, language, crime investigation, trial, and judicial procedure. Applications of forensic linguistics include voice identification, interpretation of expressed meaning in laws and legal writings, analysis of discourse in legal settings, interpretation of intended meaning in oral and written statements, authorship identification and interpretation and translation when more than one language must be used in a legal context.” Forensic stylistics is the application of the science of linguistic stylistics to forensic contexts. Common features of style include the use of dialogue, including regional tones and pronunciation and individual dialects (or ideolects), the use of grammar which includes the observation of active voice and passive voice, the use of particular language registers, the distribution of sentence lengths and etc. Stylometrics is a development of literary stylistics, which is based on the assumption that all authors have individual writing habits. These writing habits can be seen in features such as core vocabulary use, phraseology and sentence complexity and all these features are unconscious habits which are well ingrained. Furthermore, it is also concerned with locating textual features which can be used for determining authorship of a text/ writings. This is achieved by having a sample of known authored texts from different authors which can be compared to a disputed text. Stylometrics is a quantitative analysis [2-5]. Thus, Stylometric approaches seek to find or describe quantifiable markers of authorship, which in the general sense vary more between authors than within authors. Typical stylometric markers include relative frequencies of different word classes or even non word letter clusters. The style markers can be categorized as character-based, word-based, sentence- based, document based, structural or syntactic. A few examples of style markers include: function word usage (common adverbs, auxiliary verbs, conjunctions, prepositions and pronouns); word collocations; sentence length and punctuation. Author identification, is the task of determining the author of a piece of work. There are following two types of variation that a forensic expert faces Intra-author variation refers to the ways in which an author’s text differs from another text written by the same author, whereas inter-author variation refers to the ways texts vary between different authors. However, in this study, the only causes of variation that could have any bearing are time lapse, if some time has passed between posts, and change in circumstances if the writer has undergone any recent changes in her life. Despite Facebook being a social networking site, there could be socio metric parameters, as it is common for an individual to have on Abbreviations :IM: Instant Messaging; WST: Wordsmiths Tools