Performance Analysis Graph-Based Keyphrase Extraction in Indonesia Scientific Paper
Riris Bayu Asrori, Robert Setyawan, Muljono Muljono · 2020 International Seminar on Application for Technology of Information and Communication (iSemantic) · 2020
The increasing number of research papers from Indonesia and the higher the need to manage large amounts of documents, including memory capacity and the availability of time to manage research documents, keyphrase can provide a picture representing a text document. Thus, the management of documents in large quantities will become easier to prepare and find a collection of documents. For this reason, proper and correct keyphrase extraction can assist in managing paper documents. This study tried to compare three extraction methods using unsupervised graph-based techniques, including TextRank, TopicRank, and PositionRank. We compare the extraction results with the keyphrase made by the authors of the paper to see the three method's performance. From the results of our research, we found that the method TextRank Providing the highest performance compared to other methods using the ROUGE test with average Recall, Precision, and F1-Score are 0.558, 0.71, and 0.225. However, the extracted phrases are longer compared to others. The performance of TopicRank, although it does not provide higher results with TextRank, the extracted keyphrase is more compact than TextRank and PositionRank methods.