Abstract | ||
---|---|---|
We present an analysis and visualization method for computing what distinguishes a given document collection from others. We determine topics that discriminate a subset of collections from the remaining ones by applying probabilistic topic modeling and subsequently approximating the two relevant criteria distinctiveness and characteristicness algorithmically through a set of heuristics. Furthermore, we suggest a novel visualization method called DiTop-View, in which topics are represented by glyphs topic coins that are arranged on a 2D plane. Topic coins are designed to encode all information necessary for performing comparative analyses such as the class membership of a topic, its most probable terms and the discriminative relations. We evaluate our topic analysis using statistical measures and a small user experiment and present an expert case study with researchers from political sciences analyzing two real-world datasets. |
Year | DOI | Venue |
---|---|---|
2014 | 10.1111/cgf.12376 | Comput. Graph. Forum |
Field | DocType | Volume |
Glyph,ENCODE,Information retrieval,Visualization,Computer science,Visual analytics,Heuristics,Topic analysis,Discriminative model,Optimal distinctiveness theory | Journal | 33 |
Issue | ISSN | Citations |
3 | 0167-7055 | 14 |
PageRank | References | Authors |
0.52 | 32 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Daniela Oelke | 1 | 225 | 13.18 |
Hendrik Strobelt | 2 | 387 | 21.65 |
Christian Rohrdantz | 3 | 205 | 13.86 |
Iryna Gurevych | 4 | 2471 | 189.26 |
Oliver Deussen | 5 | 2852 | 205.16 |