應用類別對照之資料融合方法於機器學習研究分類
Exploring Class Mapping as Data Fusion Technique in Machine Learning for Research Classification
國立臺灣大學圖書資訊學系
(Department of Library and Information Science, National Taiwan University, Taipei, Taiwan)
摘要
訓練機器學習分類模型須充足且高品質的資料,本研究探討類別對照作為資料融合策略,發展研究分類之機器學習模型,以2008年版與2020年版之澳洲與紐西蘭標準研究分類表為研究標的,從8家機構典藏系統蒐集179,431筆已分類文件,對二版本分類表分別建立原始資料集,及以類別對照方式擴增之資料集。結果顯示49%的2008年版文件可明確對應至2020年版,反之則為63%。進一步以SVM、SciBERT、ModernBERT-base與ModernBERT-large建立分類模型,相較僅採用原始資料集,各模型經擴增資料集訓練後,分類效能均獲改進;以ModernBERT-large表現最為顯著,其大類層級提升1.0%或2.5%,中類層級增益4.4%或2.2%,小類層級改善9.9%或11.5%,未擴增之類別亦提高32.0%或15.5%。整體而言,類別對照可用於擴展訓練資料,提升自動研究分類效能。
Abstract
Access to sufficient, high-quality data is essential for effectively training and validating machine learning classifiers. This study investigates class mapping as a data fusion strategy to enhance training data for research classification. Two versions of the Australian and New Zealand Standard Research Classification, ANZSRC 2008 FoR and ANZSRC 2020 FoR, are used to organize 179,431 documents from eight institutional repositories into plain and mapped datasets. Each dataset is divided into subsets corresponding to the division, group, and field levels of the classification schemes. Results show that 49% to 63% of documents are successfully mapped between schemes. Classifiers by Support Vector Machines (SVM), SciBERT, ModernBERT-base, and ModernBERT-large are trained to assess the effectiveness of this data fusion approach on classification performance. All models show improved performance at the three levels. ModernBERT-large achieved the greatest performance gains, with the improvements in validation F1 scores of 1.0% and 2.5% at the division level, 4.4% and 2.2% at the group level, and 9.9% and 11.5% at the field level. An emergent ability was observed, as performance in non-augmented classes improved with ModernBERT-large but not with ModernBERT-base. Overall, this study demonstrates that class mapping effectively enriches training datasets, enhances classification performance, and underscores the importance of model size and architecture. These findings offer a practical and scalable strategy for improving machine learning performance in research classification tasks.
關鍵詞
- 類型
- 論文
- 期刊
- 圖書資訊學刊
- ISSN
- 1606-7509
- 卷期
- 23卷2期
- 出版
- 2025年12月
- 頁碼
- 119–143
- 編號
- NTUEJ00004467
同期目錄
- 腦波圖在網路搜尋研究中的應用:針對樣本大小、活躍作者和研究結果的系統性回顧Mahsa Torabi・頁 001–045
- 元宇宙數位策展之歷史事件體驗提升歷史學習成效陳志銘(Chih-Ming Chen);藍適齊(Shi-Chi Lan);李明娟(Ming-Chaun Li);翁榮秀(Jung-Hsiu Weng)・頁 047–083
- 疫情期間大學生由社群媒體接收錯誤訊息之資訊行為分析林麗娟(Lih-Juan ChanLin)・頁 085–118
- 應用類別對照之資料融合方法於機器學習研究分類黃建智(Chien-Chih Huang);陳光華(Kuang-Hua Chen)・頁 119–143
- 賦權國小國語文學習:利用大型語言模型生成符合專業觀點的客製化教材連大成(Da-Chen Lian);古貿昌(Mao-Chang Ku);王伯雅(Po-Ya Angela Wang);陳韋伶(Wei-Ling Chen);謝舒凱(Shu-Kai Hsieh)・頁 145–183
- 資料密集視角下的臺灣公民科學計畫:整體實踐與品質維護策略鄭瑋(Wei Jeng);甘婕人(Chieh-Jen Kan);黃寶霈(Pao-Pei Huang);陳靖瑄(Ching-Hsuan Chen)・頁 185–217
- 工作輪調對圖書館館員留任意願之影響:以工作特性與滿意度為中介變數廖子平(Tz-Ping Liao);柯皓仁(Hao-Ren Ke)・頁 219–257
- 蓮瓣辟蠹的文獻記載與實踐林振岳(Zhen-Yue Lin)・頁 259–282
- 《山東軍興紀略》作者及版本辨正王雨非(Yu-Fei Wang)・頁 283–307