Cross Platform Modeling of Users’ Behavior on Social Media

With the booming development and popularity of mobile purposes, alternative verticals collect abundant data of user tips and social behavior, which are spontaneous, true and varied. However, each platform describes user’s graphics in exactly bound aspect, resulting in challenging combination of these web footprints together. Moreover, with the aid of user data of Weibo, correlations between music preference i. e.

genre, mood and Big Five personalities BFPs and basic advice e. g. gender, resident region, tags were comprehensively studied, build up full scale user pics with finer grain. With the booming advancement and popularity of mobile purposes, differentverticals acquire abundant data of user assistance and social conduct,which are spontaneous, precise and diversified. However, each platformdescribes user’s pictures in precisely sure aspect, resulting in difficultcombination of those cyber web footprints together.

In our analysis, we proposeda modeling method to examine user’s online conduct across different socialmedia structures. Structured and unstructured data of same users shared byNetEase Music and Sina Weibo have been accumulated for cross platform evaluation ofcorrelations between music option and other users’ features. Basedon music tags of genre and mood, genre cluster of 5 groups and mood clusterof four groups were formed by computing their accumulated song lists withK means method. Moreover, with the help of user data of Weibo, correlationsbetween music preference i. e.

genre, mood and Big Five personalities BFPsand basic information e. g. gender, resident region, tags have beencomprehensively studied, increase full scale user pictures with finergrain. Our findings point out that folks’s music selection could be linkedwith their real social activities. For instance, people living in mountainousareas generally prefer folk music, while those in urban areas like pop musicmore.

Interestingly, dog lovers could love sad music greater than cat lovers. Moreover, our proposed cross platform modeling approach could be adapted toother verticals, offering an internet automatic way for profiling users in amore precise and complete way. With the booming advancement and approval for mobile applications, different verticals collect plentiful data of user assistance and social conduct, which are spontaneous, true and various. However, each platform describes user’s snap shots in precisely bound aspect, resulting in challenging aggregate of these cyber web footprints in combination. In our analysis, we proposed a modeling strategy to examine user’s online behavior across alternative social media structures. Structured and unstructured data of same users shared by NetEase Music and Sina Weibo have been accrued for cross platform evaluation of correlations among music option and other users’ features.

See also  Factual InMobi Inks Global Partnership with Factual to Increase Mobile Ad Efficacy for Brands

Based on music tags of genre and mood, genre cluster of 5 groups and mood cluster of 4 groups have been formed by computing their accrued song lists with K means method. Moreover, with the aid of user data of Weibo, correlations between music alternative i. e. genre, mood and Big Five personalities BFPs and basic guidance e. g.

gender, resident region, tags have been comprehensively studied, increase full scale user snap shots with finer grain. Our findings point out that people’s music preference may be linked with their real social activities. For instance, people living in mountainous areas commonly prefer folk music, while those in urban areas like pop music more. Interestingly, dog lovers could love sad music more than cat lovers. Moreover, our proposed cross platform modeling strategy may be tailored to other verticals, providing an internet computerized way for profiling users in a more precise and comprehensive way.