Emerging Topic Detection Model Based on LDA and Its Application in Stem Cell Field

Abstract

Based on the investigation above background of stem cell research, this paper obtains the research topics of different time-window series with LDA topic segment model, and then the emerging topics are identified and judged according to the assumption of emerging topic definition. This paper proposes a new method to detect and identify the emerging topic in the topic evolution model. In this method, first, the time of the whole dataset is divided into several time-window series, and then the topics in total time-windows are segmented by LDA model. The composite relationships between topics are calculated by integrating the relationships of consistency, co-occurrence and semantics between topics. Those composite relationships are used to indicate and visualize the evolutionary relationships among topics. The emerging topics are detected by analyzing the characters of different evolutionary types including topics' differentiation, integration, emerging and decrease. And then the model's effectiveness is verified by case study in the stem cell field and expert judgment. Finally, the model's disadvantages and the next jobs are introduced in the paper.

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 — 1 citations exist upstream.

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