A novel emerging topic detection method: A knowledge ecology perspective

Abstract

Emerging topic detection has attracted considerable attention in recent times. While various detection approaches have been proposed in this field, designing a method for accurately detecting emerging topics remains challenging. This paper introduces the perspective of knowledge ecology to the detection of emerging topics and utilizes author-keywords to represent research topics. More precisely, we first improve the novelty metric and recalculate emergence capabilities based on the “ecostate” and “ecorole” attributes of ecological niches. Then, we take the perspective that keywords are analogous to living bodies and map them to the knowledge ecosystem to construct an emerging topics detection method based on ecological niches (ETDEN). Finally, we conduct in-depth comparative experiments to verify the effectiveness and feasibility of ETDEN using data extracted from scientific literature in the ACM Digital Library database. The results demonstrate that the improved novelty indicator helps to differentiate the novelty values of keywords in the same interval. More importantly, ETDEN performs significantly better performance on three terms: the emergence time point and the growth rate of pre-and post-emergence.

Introduction

The knowledge environment is constantly evolving and developing; new knowledge constantly emerges while old knowledge becomes obsolete. The evolution of knowledge discriminates between old and new knowledge by selecting those knowledge units that fit the environmental constraints in which they live (Firestone, 2008). Like organisms, knowledge units experience a full life cycle, which generally includes creation, mobilization, diffusion, and integration. (Stary, 2014). Furthermore, this process has been also subtly summarized as a four-stage S-shaped curve: birth, growth, maturity, and senility (Braun et al., 2000; Van den Oord & Van Witteloostuijn, 2018). Therefore, the evolution of knowledge units in a knowledge ecosystem follows certain universal laws that provide strong theoretical support for detecting emerging research topics.

The study of emerging topic detection has tended to primarily focus on the design of bibliometric indicators that reveal the nature of emergence (Xu et al., 2019). More specifically, many bibliometric indicators for identifying emerging topics from different aspects have been proposed, such as novelty (Tu & Seng, 2012; Wang, 2018; Porter et al., 2019), growth (Ohniwa & Hibino, 2010; Coccia, 2012; Dang et al., 2016), community (Yu et al., 2016; Yoon et al., 2018; Yoo et al., 2019), and uncertainty (Yu et al., 2016). It has been observed that the novelty and growth indicators often appear in the scientific literature on emerging topic detection. However, the indicators proposed in each article above are different and arbitrary, which may result in the lack of well-established linkages between the concept of an emerging topic and these operationalization indicators (Xu et al., 2019). Thus, to accurately detect emerging research topics, an alternative idea should be used to re-examine extant studies. Scientific exploration was conceptualized as a search in a high-dimensional abstract landscape of problems. There exists a clear analogy with the spatial model of evolutionary biology (Börner & Scharnhorst, 2009). Several computational models and basic theories from evolutionary biology can be employed in the study of topic evolution. Researchers were inspired to explore the evolutionary laws of research topics from an ecological perspective (Van den Oord & Van Witteloostuijn, 2018). These studies are instructive in terms of exploring a novel method of emerging topic detection. Namely, the ecological niche theory can be used during the process of detecting emerging topics from a knowledge ecology perspective.

The primary objective of this study is to propose a novel method of emerging topics detection from the perspective of knowledge ecology. More specifically, we first introduce the ecological niche theory to extend the idea of emerging topic detection, which provides two dimensions for classifying bibliometric indicators based on the “ecostate” and “ecorole” attributes. Second, we improve the novelty indicator using a weighting modified method to differentiate the novelty values of research topics in the same interval; we also calculate the slope value of growth at the detection point (niche value) to represent the emergence capability in terms of the “ecorole” attribute of ecological niches. Third, keywords are analogized with living bodies and mapped to the knowledge ecosystem to construct a niche baseline for detecting emerging topics. Finally, we conduct in-depth comparative experiments to verify the effectiveness and feasibility of our approach using data extracted from scientific literature in the ACM Digital Library database.

The rest of this paper is organized as follows: Section 2 reviews ecological niche theory and knowledge ecology, previous studies on bibliometric indicators of emerging topics, and keyword-based emerging topic detection. Section 3 describes the material and methods. Section 4 primarily discusses the study's results. Finally, we conclude with an overview of our findings and implications in Section 5.