Market-Required Competence Topic Dynamics

2017

The Labour Market domain is a relatively narrow domain in terms of concept types that appear in it (as it typically consists of professions, skills and qualifications) but a very broad one in terms of actual concepts (as these professions and skills can be in all kinds of domains such as Technology, Education, Finance, etc). More importantly, it is a quite volatile domain in the sense that the meaning of many concepts changes (at different rates) over time. This phenomenon, known as semantic or concept drift, poses a challenge for the maintenance and evolution of knowledge graphs that represent such domains, and requires dedicated approaches for tackling it so as to prevent such graphs from becoming irrelevant. With that in mind, in this paper we describe our experiences from dealing with concept drift in an in-house developed labour market knowledge graph, and provide insights on: i) how concept drift can be effectively defined and modeled for labour market concepts, and ii) how it...

Journal of Mekong Societies, 2021

Most research data in the modern world are in digital format, and there is therefore a need to develop high-efficiency tools that can provide access to and an understanding of these data. Computerization technology based on natural language processing with a capacity for topic extraction and categorization would enable us to identify new topics and future directions for research in several fields of study. The aim of this research was to analyze and categorize information science research data obtained from journals listed in an international database between 2013 and 2019. The research methodology applied here was data analysis based on the topic modeling method, a technique used to locate word groups or topics from a corpus containing complicated and difficult works. This method yields reliable and high-accuracy outcomes. The data analyzed here were drawn from research articles published in information science journals, the names of which were listed in the Scimago Journal and Country Rank between 2013 and 2019. Only journals in the Web of Science and articles written in English were included. A total of 30,571 research articles obtained from 677 volumes of 99 journals were analyzed using the topic modeling method, and topics were assigned by experts in the field. The findings revealed that over the past seven years, research was carried out on 30 topics in information science. The five most frequently researched topics were competency development, data management, social media analytics, public and community services, and bioinformatics. A comparison with other research data analyzed in the field of information science over the past five years using other techniques showed clear differences and a tendency of the research topics to change. The results of this research can greatly benefit the identification of research directions for the future.

Academy of Management Annals

The nested Chinese restaurant process is extended to design a nonparametric topic-model tree for representation of human choices. Each tree path corresponds to a type of person, and each node (topic) has a corresponding probability vector over items that may be selected. The observed data are assumed to have associated temporal covariates (corresponding to the time at which choices are made), and we wish to impose that with increasing time it is more probable that topics deeper in the tree are utilized. This structure is imposed by developing a new "change point" stick-breaking model that is coupled with a Poisson and productof-gammas construction. To share topics across the tree nodes, topic distributions are drawn from a Dirichlet process. As a demonstration of this concept, we analyze real data on course selections of undergraduate students at Duke University, with the goal of uncovering and concisely representing structure in the curriculum and in the characteristics of the student body.

2020

Modeling the interests of researchers in academic social networks is a crucial step in a process of recommending scientific articles, linked to their areas of competence and expertise. In this context, a researcher profile constructed from non-observable variables on the basis of articles which interests him by the LDA (Latent Dirichlet Allocation) topic modeling technique allows the system to capture knowledge about his area of competence and skills, in order to predict these needs in terms of relevant research articles. In this article we are interested in the results produced by two different implementations of LDA Gensim and Mallet on the basis of information provided by the researchers (explicit information), in order to compare their interpretability and checked if they are reliable sources for model the areas of competence and expertise of scientists. Keywords-1 st Topic Modeling, 2 nd LDA , 3 rd Mallet, 4 th Researcher Profil.

Risk Management and Decision-Making, 2014

Topic models are probabilistic models for discovering topical themes in collections of documents. In real world applications, these models provide us with the means of organizing what would otherwise be unstructured collections. They can help us cluster a huge collection into different topics or find a subset of the collection that resembles the topical theme found in an article at hand.

Journal of Big Data, 2022

Introduction Fast-emerging technologies are making the job market dynamic, causing desirable skills to evolve continuously. It is therefore important to understand the transitions in the job market to proactively identify skill sets required. Case description A novel data-driven approach is developed to identify trending jobs through a case study in the oil and gas industry. The proposed approach leverages a range of data analytics tools, including Latent Semantic Indexing (LSI), Latent Dirichlet Allocation (LDA), Factor Analysis and Non-Negative Matrix Factorization (NMF), to study changes in the market. Further, our approach is capable of identifying disparities between skills that are covered by the educational system, and the skills that are required in the job market. Discussion and evaluation The results of the case study show that, while the jobs most likely to be replaced are generally low-skilled, some high-skilled jobs may also be at risk. In addition, mismatches are ident...

Journal of Economics Methdology, 2018

The paper presents the topic modeling technique known as Latent Dirichlet Allocation (LDA), a form of text-mining aiming at discovering the hidden (latent) thematic structure in large archives of documents. By applying LDA to the full text of the economics articles stored in the JSTOR database, we show how to construct a map of the discipline over time, and illustrate the potentialities of the technique for the study of the shifting structure of economics in a time of (possible) fragmentation

IEEE Access

Topic modeling is a Natural Language Processing technique that has gained popularity over the last ten years, with applications in multiple fields of knowledge. However, there is insufficient empirical evidence to show how this field of study has developed over the years, as well as the main models that have been applied in different contexts. The objective of this paper is to analyze the evolution of the topic modeling technique, the main areas in which it has been applied, and the models that are recommended for specific types of data. The methodology applied is based on bibliometric analysis. First, we searched the Web of Science and the Scopus databases. We then used scientometric techniques and a Tree of Science methodology, which allowed us to analyze the search results from the perspectives of classics, structure, and trends. The results show that the USA and China are among the most productive countries in this field and the applications have been mainly in the identification of sub-topics in short texts, such as social networks and blogs. The main conclusion of this work is that topic modeling is a versatile technique that can complement systematic literature reviews and that has been well-received in different academic and research contexts. The results of this study will help researchers and academics to recognize the importance of these techniques for reviewing large volumes of unstructured information, such as research articles, and in general, for systematic literature reviews. INDEX TERMS Literature review, machine learning, natural language processing, scientometrics, topic modeling.

Through recognizing the importance of a qualified workforce, skills research has become one of the focal points in economics, sociology, and education. Great effort is dedicated to analyzing labor demand and supply, and actions are taken at many levels to match one with the other. In this work we concentrate on skills needs, a dynamic variable dependent on many aspects such as geography, time, or the type of industry. Historically, skills in demand were easy to evaluate since transitions in that area were fairly slow, gradual, and easy to adjust to. In contrast, current changes are occurring rapidly and might take an unexpected turn. Therefore, we introduce a relatively simple yet effective method of monitoring skills needs straight from the source—as expressed by potential employers in their job advertisements. We employ open source tools such as RapidMiner and R as well as easily accessible online vacancy data. We demonstrate selected techniques, namely classification with k-NN and information extraction from a textual dataset, to determine effective ways of discovering knowledge from a given collection of vacancies.