VISUALLY ENHANCED SOCIAL MEDIA ANALYSIS OF REFUGEES IN TURKEY
Abdullah Bülbül, A. Haj Ismail · DergiPark (Istanbul University) · 2018
Thepopulation of refugees in Turkey is significantly growing since 2014 and it hasalready exceeded three millions. This situation urges to study their conditionsand issues as well as their opinions. In this study, we propose a method toanalyze the dataset collected from social media accounts of refugees in Turkeyin a textual and visual manner. Firstly, we acquire social media activities ofrefugees, and then we make textual analysis for which the results are presentedusing word clouds. Finally, for the most significant words obtained from thetextual analysis, we perform a visual analysis to find out the mostrepresentative image or a group of images shared in social networks. Theassociation between textual and visual results enhances their perceptibilityand help decreasing the ambiguity of inferences over analysis results. Weexperimented with different scenarios and suggested several methods to enhancecomputational and qualitative results.