Refining the Measurement of Topic Similarities Through Bibliographic Coupling and LDA

Abstract

Generally, two topics with vastly different terminology probably indicate different implied concepts. However, these topics themselves might share common references (bibliographic coupling), which suggest the underlying joint concept. Therefore, searching for these joint concepts in different topics would be of scientific interest. Previous studies have measured the similarity between topics based on comparison of the topics' word probability distributions. In contrast, this paper presents an approach for measuring the similarity between topics based on the bibliographic coupling. Besides, the similarity is independent of the topic's word probability distributions generated by a Latent Dirichlet Allocation (LDA) model. The proposed approach was evaluated using its counterpart (intra-topic similarity), baseline topic similarity matrices, and cosine measure. The method was exampled on brain cancer patents. A cross-topic similarity network of eight topics showcases 28 cross-topic pairs to profile which topics were associated with particular topics. Interestingly, some of the 28 combinations may be of scientific interest. For instance, the findings of the top five cross-topic pairs suggest that “growth of cancer cells” and “imbalances in the hormones” have common knowledge sources with the highest similarity value. These two entirely different concepts may suggest some common causative factors within the field. We believe that finding such an association between unrelated innovative inventions across various industries may help public and private research units in planning research direction and serve as a reference for future research.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 6 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.