Main Article Content
With the spread of Big data, there is an increasing interest in Unstructured Data analysis techniques, and studies are being carried out to extract valuable information from vast amounts of academic data. Most passive analysis of large texts by humans is time consuming and laborious and difficult, so a technique that can automatically classify them in order to supplement them is needed. Therefore, this study analyzed and visualized by using Unstructured Data such as the main words, thesis title, and abstract of ‘Korean Journal of Industrial and Organizational Psychology’ published from 2010 to 2017. The results of the study are as follows. First, ‘organizational commitment’ was frequently used as a result of visualization of the key words using wordcloud. Job satisfaction, job enthusiasm, turnover intention, emotional labor showed the order. Second, the title of the paper and the abstract were automatically classified into 10 topics based on the LDA probability. Topic 8(organization/commitment/perception) was the highest, and Topic 5(behavior/management/boss) was the lowest. Third, the relationship between the main author and the correspondent author appeared as six large groups and several small groups. We were able to identify influential authors within the group. In this study, it is suggested that related researchers can get access to another research by deriving information from a vast amount of academic data more quickly and easily.
This work is licensed under a Creative Commons Attribution 4.0 International License.