Maps of Computer Science
This provides a tool for researchers and institutions to analyze and visualize trends in computer science literature, though it is incremental as it applies existing NLP and IR methods to a new visualization context.
The paper tackles the problem of visually exploring research papers by creating maps of computer science using titles from the DBLP database, with words as cities and countries based on similarity, and demonstrates applications like visualizing conference profiles and research evolution through heatmaps.
We describe a practical approach for visual exploration of research papers. Specifically, we use the titles of papers from the DBLP database to create what we call maps of computer science (MoCS). Words and phrases from the paper titles are the cities in the map, and countries are created based on word and phrase similarity, calculated using co-occurrence. With the help of heatmaps, we can visualize the profile of a particular conference or journal over the base map. Similarly, heatmap profiles can be made of individual researchers or groups such as a department. The visualization system also makes it possible to change the data used to generate the base map. For example, a specific journal or conference can be used to generate the base map and then the heatmap overlays can be used to show the evolution of research topics in the field over the years. As before, individual researchers or research groups profiles can be visualized using heatmap overlays but this time over the journal or conference base map. Finally, research papers or abstracts easily generate visual abstracts giving a visual representation of the distribution of topics in the paper. We outline a modular and extensible system for term extraction using natural language processing techniques, and show the applicability of methods of information retrieval to calculation of term similarity and creation of a topic map. The system is available at mocs.cs.arizona.edu.