Text
KLASIFIKASI AUTHOR MATCHING PADA DATA BIBLIOGRAFI MENGGUNAKAN METODE RECURRENT NEURAL NETWORK
In bibliographic data analysis, accurate author matching is crucial for various applications such as citation analysis and research profiling. This research focuses on the classification of author matching in bibliographic data using RNNs method. By leveraging the power of RNNs, the authors aim to improve the accuracy of author matching classification in two specific scenarios: homonym and synonym cases. The authors utilize parameters such as Author, Co-Author, Title, Year, and Venue. In the homonym case, the authors achieved an excellent accuracy rate of 96.19% using the best-performing model. This high accuracy demonstrates the effectiveness of the RNNs method in distinguishing between authors with similar names. Furthermore, the authors also investigated the synonym case, where authors may have different names but refer to the same entity. In this scenario, they obtained a good accuracy rate of 9.81%, indicating the potential of RNNs in identifying synonymous authors in bibliographic data. Overall, this research highlights the important role of RNNs in author matching classification in bibliographic data. Despite using non-tabular data, the results demonstrate the effectiveness of this method in distinguishing between authors with similar names, both in homonym and synonym cases.
Inventory Code | Barcode | Call Number | Location | Status |
---|---|---|---|---|
2307001917 | T105878 | T1058782023 | Central Library (Referens) | Available but not for loan - Not for Loan |
No other version available