Text Mining of Computer Engineering Articles Based on the Documents Retrieved from the Web of Science Database

The aim of this study was to evaluate text mining and clustering of computer engineering documents retrieved from the Web of Science database. This is a descriptive-analytical study which was conducted in a survey method using text mining approach. The research community was all computer engineering documents indexed in the Web of Science, among which 6016 cases were reported between 2004 and 2016. The collected data were analyzed by HistCite software, Excel version 2013 and RapidMiner version 7.3. In order to perform clustering, after preprocessing the data and running K-means (a clustering algorithm), 8 main clusters were established. The clusters were Internet and Technology, Security of Healthcare Information Systems, Human-Computer Interaction, Semantic Web, Computer Models, Computer Systems Performance, Networks & Databases, Knowledge Discovery Algorithms and Other Topics. To evaluate the clusters, two criteria of precision and recall were used and a value of 0.81 was obtained for both criteria. Using words selected as keywords in the clustering can help the user save time and retrieve the related information.