Pelatihan Optimalisasi Pemanfaatan AI Berbasis Scite.Ai Untuk Penulisan Literatur Review

Nurfaika Nurfaika, M. Iqbal Liayong Pratama

Abstract


This community service activity aimed to enhance the competencies of Master’s students in Geography Education at the Graduate School of Universitas Negeri Gorontalo (UNG) in optimizing the use of Artificial Intelligence (AI), particularly Scite.ai, for literature review writing. The main issue identified was the participants’ limited understanding of AI-based tools for reference searching and systematic, evidence-based literature synthesis. The program employed a participatory hands-on training approach involving six active graduate students and was conducted at the Graduate Lecture Building of UNG. Evaluation was carried out using pre-test and post-test assessments to measure competency improvement. The pre-test results indicated that 0% of participants understood how to use Scite.ai for contextual citation analysis. After the training and practical sessions, post-test results demonstrated that 100% of participants were able to independently use the application and successfully produce a complete Chapter II (Literature Review) draft aligned with their respective thesis topics. The activity proved effective in improving AI literacy, contextual citation analysis skills (supporting, contrasting, mentioning), and the overall quality of academic argumentation. Continuous implementation of similar training programs is recommended to support research quality enhancement and scholarly publication in higher education institutions.


Keywords


Artificial Intelligence; Scite.AI; Literature Review; Academic Training; Digital Literacy; Contextual Citation Analysis

Full Text:

PDF

References


Bawden, D., & Robinson, L. (2009). The dark side of information: Overload, anxiety and other paradoxes and pathologies. Journal of Information Science, 35(2), 180–191. https://doi.org/10.1177/0165551508095781

Bornmann, L., & Daniel, H.-D. (2008). What do citation counts measure? A review of studies on citing behavior. Journal of Documentation, 64(1), 45–80. https://doi.org/10.1108/00220410810844150

Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019). BERT: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (pp. 4171–4186). https://doi.org/10.18653/v1/N19-1423

Small, H. (1978). Cited documents as concept symbols. Social Studies of Science, 8(3), 327–340. https://doi.org/10.1177/030631277800800305

Van Eck, N. J., & Waltman, L. (2014). Visualizing bibliometric networks. In Y. Ding, R. Rousseau, & D. Wolfram (Eds.), Measuring scholarly impact: Methods and practice (pp. 285–320). Springer. https://doi.org/10.1007/978-3-319-10377-8_13




DOI: https://doi.org/10.37905/jrpi.v3i1.37400

Refbacks

  • There are currently no refbacks.


Copyright (c) 2025 Nurfaika Nurfaika, M. Iqbal Liayong Pratama

Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 International License.