Towards employing native information in citation function classification

Measuring security development in information technologies: A scientometric framework using arXiv e-prints

“…Some studies rely on indicators such as bibliometric analyses related to scientific publications (i.e., scientometrics) (Zhang et al, 2020b,a;Mayr et al, 2014;Dotsika and Watkins, 2017;Jaewoo and Woonsun, 2014;Rezaeian et al, 2017), patents (Hajikhani and Suominen, 2022;Choi et al, 2022;Chen et al, 2017;Golembiewski et al, 2015;Noh et al, 2016;An et al, 2018;Lee and Lee, 2019;Song et al, 2017), industrymarket indicators (job openings, trade registers, networks of authors and citations), or a combination of these (An et al, 2022;Xi et al, 2022;Ali et al, 2022;Daim et al, 2012;Lee et al, 2010). To analyze this data, text-mining methods (Chen et al, 2017;Choi and Hwang, 2014;Hao et al, 2014;Antons et al, 2020) and network analysis (Chen et al, 2022;Zhang et al, 2022;Li et al, 2019b;Mikheev, 2020;Feng et al, 2022;Hong et al, 2021) are particularly prolific. For instance, Guo, Wang, Tian, and Xian (2019) analyze 1666 scientific publications to detect trends in network technologies and information systems (Guo et al, 2019).…”

An editorial of “AI + informetrics”: multi-disciplinary interactions in the era of big data

“…Identifying core features from a reference's limited information and constructing evaluation models to measure references are among the top challenges. Zhang et al (2022) emphasized the value of a reference's native information (e.g., citation context and section name), and integrated these features into different neural text representation models. Based on a dataset with labeled citations, the improved classification performance endorsed the effectiveness of their efforts on feature selection and representation.…”