Creating a Visual Topic Map for Battery Researchers Using a Large Global Open Dataset

• DOI: 10.1149/ma2023-0283321mtgabs
• Publication Date: 2024-02-08T19:23:25Z
• Authors: Sae Dieb; Luca Foppiano; Keitaro Sodeyama; Mikiko Tanifuji

Battery related research has gained increasing attention in recent years. A large number of papers about battery are being published as open access. In order to explore the content these efficiently, it is necessary develop information management tools capture knowledge embedded them. We working on a project create visual topic map for researchers. This connects researchers according their topics. allows potential connection between researches with similar topics, which increase collaboration opportunities advance research. Additionally, visualization supports intuitive capturing trend by maximizing absorbance. extract all works from OpenAlex 1 , fully catalog global that offers significant advantages terms data coverage and affordability openness. Anther important feature that, every article tagged multiple concepts using automatic classifier. addition extracted dataset, we used pre-trained language model, named KeyBERT 2 further representative work abstract. minimal easy-to-use keyword extraction technique based transformers model. For each researcher, have articles authored author. Using those concepts, formulate vector researcher represents total output. To find interests, measure similarity vectors authors space. Top matching connected visually expands over topics Figure shows snapshot this map. Researchers names were hidden privacy purposes. Priem, J., Piwowar, H., & Orr, R. (2022). OpenAlex: fully-open index scholarly works, authors, venues, institutions, . ArXiv. https://arxiv.org/abs/2205.01833 Grootendorst, M. (2020). KeyBERT: Minimal BERT. https://doi.org/10.5281/zenodo.4461265