Clustering student Instagram accounts using author-topic model

Abstract

Intense use of Instagram among young adolescent showed that the usage of social media is not limited to the following trend, but are also becoming a need for showing existence to the public. The aim of this study proposes a topic model to cluster a group of high school teenager's Instagram account in Surabaya, Indonesia by using the Author-Topic Models method. For data collection, a paper and pencil questionnaire was applied to this study to collect valid 235 Instagram account (133 female and 102 male students). The data crawling gathers a total 3,346 captions of the Instagram post from 18 senior high schools. We find major findings what are topics that define their Instagram's post or caption, seven topics namely: Feeling, Surabaya Events, Photography, Artists, Vacation, Religion and Music. Through the process, the best result is from 90 iterations, which suggests six group of topics. The six topics are concluded based on the lowest perplexity value and labelled according to the words included in the topic. Another findings show that there are three schools discussed "Feeling", two schools discussed "Surabaya Events". The "Photography" topic is discussed by six schools, "Photography and Artists" and "Vacation" each are discussed by three schools, and "Religion and Music" by one school.