Co-Occurrence-Based Double Thresholding Method for Research Topic Identification

Abstract

Identifying possible research gaps is a main step in problem framing, however it is increasingly tedious and expensive considering the continuously growing amount of published material. This situation suggests the critical need for methodologies and tools that can assist researchers in their selection of future research topics. Related work mostly focuses on trend analysis and impact prediction but less on research gap identification. This paper presents our first approach in automated identification of feasible research gaps by using a double-threshold procedure to eliminate the research gaps that are currently difficult to study or offer little novelty. Gaps are then found by extracting subgraphs for the less-frequent co-occurrences and correlations of key terms describing domains. A case study applying the methodology for electronic design automation (EDA) domain is also discussed in the paper.

Dataset for bibliometric data-driven research team formation: Case of Politehnica University of Timisoara scholars for the interval 2010–2022

“…The information provided by the four collections of data is intended to aid in identifying the researchers’ areas of expertise and assessing both their general expertise and their level of expertise within a given area. A common practice to model areas of expertise is to use their corresponding key terms [4] that may be extracted using TagMe entity linking procedure [5] from three metadata fields, namely ‘title’, ‘keywords’, and ‘abstract’. To evaluate the suitability of using such fields in devising the key terms we offer a collection of data for each of the following four cases: Case#1: ‘title’, ‘keywords’, and ‘abstract’ fields were used to extract 6493 key terms; Case#2: ‘title’ and ‘keywords’ fields were used to extract 2651 key terms; Case#3: ‘title’ fields were used to extract 1844 key terms; Case#4: ‘keywords’ fields were used to extract 1254 key terms.…”

Automating Research Problem Framing and Exploration through Knowledge Extraction from Bibliometric Data

“…• Research gap discovery requires the analysis of the bibliographic metadata to unveil non-existent or weak links inside sets of key terms during a specified time interval [5,12]. If there is sufficient scientific knowledge to support each individual key term and the links between them remain insignificant, a possible research gap may have been identified [23]. The endeavor to discover research gaps is generally based on evaluating the time distribution of key term times and their co-occurrences in a given publication metadata corpus.…”

“…Because not every research gap is a feasible starting point for new research initiatives, it is critical to choose research gaps that provide sufficient scientific innovation prospects at that particular time moment. Various NLP and machine learning (ML) techniques and available bibliographic resources can be utilized [23].…”

Identifying Hot Information Security Topics Using LDA and Multivariate Mann-Kendall Test

“…In order to identify research topics from bibliometric data, NLP proposes various methods including document clustering [5], author co-citation analysis [6] or document classification [7]. However, the topic modeling based approach is rapidly becoming a standard in this respect and generally employs Latent Dirichlet Allocation (LDA) [8] and its variants to discover research topics from scientific publication corpora preprocessed in either bag-ofwords [9], [10], [11] or bag-of-entities [12] fashion.…”

“…Since, in our view, the research VOLUME 11, 2023 topics are more suitably modeled by sets of key terms, the use of univariate time series is inappropriate, needing to find multivariate type approaches. Our recent paper [12], solves this issue by proposing the topic trend assessment using a multivariate extension of Mann-Kendall trend test.…”