Frontline Learning Research <p>Frontline Learning Research (FLR) welcomes risk-taking and explorative studies that provide input for theoretical, empirical and/or methodological renewal within the field of research on learning and instruction. The journal offers a distinctive opening for foundational research and an arena for studies that promote new ideas, methodologies or discoveries. Read about what is frontline under <a href="" target="_blank" rel="noopener">Aims and scope</a></p> en-US <p>FLR adopts the Attribution-NonCommercial-NoDerivs Creative Common License (BY-NC-ND). That is, Copyright for articles published in this journal is retained by the authors with, however, first publication rights granted to the journal. By virtue of their appearance in this open access journal, articles are free to use, with proper attribution, in educational and other non-commercial settings.</p> (Thomas Martens) (Moritz Niemann) Wed, 14 Apr 2021 01:15:52 -0700 OJS 60 Staying at the front line of literature: How can topic modelling help researchers follow recent studies? <div> <p class="AbstractText"><span lang="EN-GB">Staying at the front line in learning research is challenging because many fields are rapidly developing. One such field is research on the temporal aspects of computer-supported collaborative learning (CSCL). To obtain an overview of these fields, systematic literature reviews can capture patterns of existing research. However, conducting systematic literature reviews is time-consuming and do not reveal future developments in the field. This study proposes a machine learning method based on topic modelling that takes articles from a systematic literature review on the temporal aspects of CSCL (49 original articles published before 2019) as a starting point to describe the most recent development in this field (52 new articles published between 2019 and 2020). We aimed to explore how to identify new relevant articles in this field and relate the original articles to the new articles. First, we trained the topic model with the Results, Discussion, and Conclusion sections of the original articles, enabling us to correctly identify 74% (n = 17) of new and relevant articles. Second, clusterisation of the original and new articles indicated that the field has advanced in its new and relevant articles because the topics concerning the regulation of learning and collaborative knowledge construction related 26 original articles to 10 new articles. New irrelevant studies typically emerged in clusters that did not include any specific topic with a high topic occurrence. Our method may provide researchers with resources to follow the patterns in their fields instead of conducting repetitive systematic literature reviews.</span></p> </div> Joni Lämsä, Catalina Espinoza, Ari Tuhkala, Raija Hämäläinen Copyright (c) 2021 Frontline Learning Research Wed, 14 Apr 2021 00:00:00 -0700