Classification of Scientific Publications using Swarm Intelligence

Document classification is an important task in data mining. Currently, identifying category (i.e., topic) of a scientific publication is a manual task. The Association for Computing Machinery Computing Classification System (ACM CCS) is most wildly used multi-level taxonomy for scientific document classification. Correct classification becomes difficult with an increase in number of levels as well as in number of categories. Domain overlapping aggravates this problem as a publication may belong to multiple domains. Thus manual classification to taxonomy becomes more difficult. Most of the existing text classification schemes are based on the Term Frequency and Inverse Document Frequency (TF-IDF) technique. Similar approaches become computationally inefficient for large datasets. Most of the techniques for text classification are not experimentally validated on scientific publication datasets. Also, multi-level and multi-class classification is missing in most of the existing schemes for document classification. The proposed approach is based on metadata (i.e., structural representation), in which only the title and keywords are considered. We reduced the features set by dropping some of the metadata, like abstract section of the scientific publication that diversifies the result accuracy. The proposed solution was inspired from the well-known evolutionary Particle Swarm Optimization (PSO). The proposed technique results in overall 84.71% accuracy on Journal of Universal Computer Science (J.UCS) dataset.