期刊名称：International Journal of Advanced Computer Science and Applications(IJACSA)
印刷版ISSN：2158-107X
电子版ISSN：2156-5570
出版年度：2019
卷号：10
期号：3
页码：513-521
DOI：10.14569/IJACSA.2019.0100366
出版社：Science and Information Society (SAI)
摘要：Due to the rapid growth of internet technologies, at present online social networks have become a part of people’s everyday life. People shares their thoughts, feelings, likings, disliking and many other issues at social networks by posting messages, videos, images and commenting on these. It is a great source of heterogeneous data. Heterogeneous data is a kind of unstructured data which comes in a variety of forms with an uncertain speed. In this paper, we develop a framework to collect and analyze a significant amount of heterogeneous data obtained from the social network to understand the behavioural patterns of the people at the social networks. In our framework, at first we crawl data from a well-known social network through Graph API that contains post, comments, images and videos. We compute keywords from the users’ comments and posts and separate keywords as noun, verb, and adjective with the help of an XML based parts of speech tagger. We analyze images related to each user to find out how a user like to move. For this purpose, we count the number of users in an image using frontal face detection classifier. We also analyze video files of the users to find the categories of videos. For this purpose, we divide each video into frames and measure the RGB properties, speed, duration, frame’s height and width. Finally, for each user we combine information from text, images and videos and based on the combined information we develop the profile of the user. Then, we generate recommendations for each user based on activities of the user and cosine similarity between users. We perform several experiments to show the effectiveness of our developed system. From the experimental evaluation, we can say that our framework can generate results up to a satisfactory level.
关键词：Heterogeneous data; recommendation systems; co-sine similarity; video categorization
