Online social media has become a vital platform to discuss common topics which are being categorised under a single name: Hashtag where people put their views, opinions and data. Thus hashtags have become a victim for spam, fake and un-related advertising content dissemination. In this paper we propose a novel approach designed on 9 distinctive parameters which extends to 4 other derived statistic from Twitter Streaming API, to detect Hashtag hijacking using Neural network analysis which shows a mean hijacking percentage of 28.5 over 10, 240 test tweets collected whereas, manual based annotation performed results in 17.14 % hijacking. Our method over collected dataset results in 94.025% accuracy. (C) 2017 The Authors. Published by Elsevier B.V.
