Understanding the research landscape of smart libraries using text mining and data visualization : A use case of Voyant Tool

Text mining has become one of the most common methods used to analyze natural language documents today. In this study, 81 open access journal articles on the topic of "smart libraries" from Google Scholar were analyzed using text mining techniques. Articles were chosen based on the criterion that they had to be open access and have smart libraries as their main component. To analyze the articles and discover interesting text patterns within the retrieved articles, Voyant Tool, an open-source text-mining tool, was used. It assists in finding Corpus Collocates that are closely related in texts as well as identifying n-grams in the field of smart libraries (sequences of words occurring together with the context that surrounds them). Results showed that the most frequently used words in the corpus were smart (3533); information (2253), data (1753); technology (1382); service (1327). Furthermore, findings showed that the longest document had 14210 words and the shortest had 1012. Overall, the study findings will help in understand the smart libraries ecosystem with deeper insight.