Bakhti, KhadidjaNiu, ZhendongNyamawe, Ally S.2024-03-272024-03-272018Bakhti, K., Niu, Z., & Nyamawe, A. S. (2018, May). Semi-automatic annotation for citation function classification. In 2018 International Conference on Control, Artificial Intelligence, Robotics & Optimization (ICCAIRO) (pp. 43-47). IEEE.DOI: https://doi.org/10.1109/ICCAIRO.2018.00016https://repository.udom.ac.tz/handle/20.500.12661/4384Full text article. Also available at https://doi.org/10.1109/ICCAIRO.2018.00016Citation function classification generally is a way to classify citations into different functions. Commonly, functions are used to determine authors purposes of citing a particular paper. Automated classification of citation functions plays a significant role in increasing educational use of citation function in scholarly publication. Due to varied informative citation, many researchers are experiencing difficulties in retrieving automatically the nature of the citations that meet their research needs. In addition, corpus builders demand tools and models that will help them carry out citation functions annotation effectively. Most of previous studies annotated the citations manually in different ways, which is often time-consuming and domain dependent. To overcome these challenges, in this paper we propose new semi-automatic annotation for citation functions classification. The proposed approach builds an annotated corpus from the citation sentences. The effectiveness of the approach is compared with existing machine-learning methods. The results indicate that our approach outperforms other methods in terms of accuracy, precision and recall.enFeature extractionLabelingMachine learningTask analysisData miningManualsSupport vector machinesArticle