Filtering of Mobile Short Messaging Service Communication Using Latent Dirichlet Allocation with Social Network Analysis  

Oleh:

Modupe, Abiodun ; Olugbara, Oludayo O. ; Ojo, Sunday O.

Jenis: Article from Books - E-Book
Dalam koleksi: Transactions on Engineering Technologies: Special Volume of the World Congress on Engineering 2013, page 671-686.
Topik: Dirichlet; Filtering; Message; Mining; Mobile; Network; Topic
Fulltext: 48_978-94-017-8831-1_Modupe_Olugbara_Ojo.pdf (596.71KB)

Isi artikel

In this study, we introduce Latent Dirichlet Allocation (LDA) with Social Network Analysis (SNA) to extract and evaluate latent features arising from mobile Short Messaging Services (SMSs) communication. This would help to automatically filter unsolicited SMS messages in order to proactively prevent their delivery. In addition, content-based filters may have their performance seriously jeopardized, because SMS messages are fairly short and their meanings are generally rife with idioms, onomatopoeias, homophones, phonemes and acronyms. As a result, the problem of text-mining was explored to understand the linguistic or statistical properties of mobile SMS messages in order to improve the performance of filtering applications. Experiments were successfully performed by collecting time-stamped short messages via mobile phones across a number of different categories on the Internet, using an English language-based platform, which is available on streaming APIs. The derived filtering system can in the future contribute in optimal decision-making, for instance, in a scenario where an imposter attempts to illegally gain confidential information from a subscriber or an operator by sending SMS messages.

Opini Anda

Klik untuk menuliskan opini Anda tentang koleksi ini!

Kembali