Mining Temporal Evolution of Knowledge Graph and Genealogical Features for Literature-based Discovery Prediction
This work addresses the challenge of predicting future scientific relations for researchers, though it is incremental as it builds on existing link prediction methods with new features.
The study tackled the problem of predicting future literature-based discoveries by forecasting emerging connections between knowledge units in scientific literature, achieving high classification performance rates.
Literature-based knowledge discovery process identifies the important but implicit relations among information embedded in published literature. Existing techniques from Information Retrieval and Natural Language Processing attempt to identify the hidden or unpublished connections between information concepts within published literature, however, these techniques undermine the concept of predicting the future and emerging relations among scientific knowledge components encapsulated within the literature. Keyword Co-occurrence Network (KCN), built upon author selected keywords (i.e., knowledge entities), is considered as a knowledge graph that focuses both on these knowledge components and knowledge structure of a scientific domain by examining the relationships between knowledge entities. Using data from two multidisciplinary research domains other than the medical domain, capitalizing on bibliometrics, the dynamicity of temporal KCNs, and a Long Short Term Memory recurrent neural network, this study proposed a framework to successfully predict the future literature-based discoveries - the emerging connections among knowledge units. Framing the problem as a dynamic supervised link prediction task, the proposed framework integrates some novel node and edge-level features. Temporal importance of keywords computed from both bipartite and unipartite networks, communities of keywords, built upon genealogical relations, and relative importance of temporal citation counts used in the feature construction process. Both node and edge-level features were input into an LSTM network to forecast the feature values for positive and negatively labeled non-connected keyword pairs and classify them accurately. High classification performance rates suggest that these features are supportive both in predicting the emerging connections between scientific knowledge units and emerging trend analysis.