日本研究資料庫與知識圖譜

The Knowledge Database/ Graph of "Japan-studies"

本研究可視化中國大陸學者的「日本研究論文資料庫」，其方法為蒐集「中國社科院」之學刊《日本學刊》之37年間2337篇論文，隨後，以其中「篇名、關鍵字、摘要」為基礎欄位（metadata）製成資料庫。 本研究並使用機器學習演算法（隱含狄利克雷分布, Latent Dirichlet Allocation, LDA)歸納《日本學刊》研究論文的「發表類型」、各類代表性關鍵字有哪些，與各年的「發表取向」有什麼變化。 本研究成功實做大量中文長文本的文字解析，並能抽取其中資料訊息，並將流程半自動化，可以達到輔助研究者快速大量理解訊息； 能抽取出高產作者、高產機構、歷年發表情形以及日本研究的主要七類範疇「金融經濟、政治、管理、文學思想、文化社會、國際關係、社會經濟」。 本研究期望能提供讀者對於某個知識領域的遠程宏觀視角，富含日本研究的方方面面「知識」，能作為學者從事日本研究之「知識庫」。 在本網站進一步提供讀者可視化訊息，將上述數據以社會網路分析（SNA）方法做出「年代-主題」、「作者-期數」、「主題-關鍵字」等等研究知識圖譜，提供學者同儕作為後續研究基礎。 如有合作需求或意見回饋，請聯繫hlshao2@gmail.com

Since studies on knowledge areas/ knowledge communities are often limited by our labor time, research cost/performance shall hence be prioritized/selected. However, our vision could be enhanced by new interdisciplinary thinking. In this article, we employed the methods of Machine Learning and Natural Language Processing to analyze 2,237 research articles. Those articles were taken from The Journal Japanese Studies published by Institute of Japanese Studies, Chinese Academy of Social Sciences (JSCASS) between 1991 and 2017. Results from the data analysis provided the answers to two questions, namely (1) what fields can be clustered in Japanese Studies, accompanied with their keywords, and (2) the number flows of the fields by year. This study analyzed thousands of Chinese long texts, and captured the key information semi-automatically, in order to efficiently support readers to approach complex information in a simplified manner. This study disclosed information on highly productive writers, highly productive institutes, their annual publications, and the main topics of Japanese Studies, which are Economics, Politics, Management Science, Literature/Ideology, Culture/Society, IR, and Social Economy. It could also provide a macro perspective in the “East Asian Studies” by new interdisciplinary thinking.

誌謝：本資料庫由科技部計畫「從知識系譜到知識地圖—大數據與機器學習下的中國研究」。
“From Knowledge Genealogy to Knowledge Map-China Studies in Big Data and Machine Learning”
107-2410-H-003 -058 -MY3, Ministry of Science and Technol-ogy, the MOST, Taiwan.

使用說明

我們的資料庫不是羅列關於期刊內容，而是進一步將其知識「體系化」。下列各欄位都可以自己輸入相關「作者/期數/關鍵字」，可以看看有沒有熟悉的人事物。在右上角有各種「知識分頁」：
A. 在「知識圖譜群組」中，提供了「作者-期數-關鍵字」的各種組合，讀者可以容易的找到「哪些學者都做什麼類型的研究」「他有哪些共通學術愛好的學者」。可以看看研究者們常投哪些期刊，以及他常常關心的議題。點點「顯示節點內容」，可以顯現更多資訊。
B. 在「作者統計/文章特性」中，讀者可以看到每個作者或文章是所有知識演變上的什麼時間、什麼位置，是使用數量式的呈現。可以很快知道每年有哪些論文。
C. 在「相似文本分析」中，你只要輸入某個關鍵字，我們會提供「相近關鍵字」與「相關文章」。我們使用了演算技巧，能夠提供近似概念，也可以接受不是完全一樣的字來「搜尋」。你也可以點選相似關鍵字（在右邊），可以擴展綿延相關知識。
D. 「主題分群分析」則是使用機器學習方式將其分群，可以知道「臺灣中國研究的主題」，知道歷年熱門的題目方向與關鍵字。

Readme

Our database does not list the content of the journal, but further "systematizes" its knowledge. You can enter the relevant "author/journal/keyword" in the "up-right" series webpages, and see if there are any familiar people and things in the research field.
A. In the "Groups of Knowledge Graph (知識圖譜群組)", various combinations of "author-journal-keywords" are provided. Readers can easily find "Which scholars do what kind of research" or "Which scholars do they have in common academic hobbies" . You can look at which journals researchers often submit to, and the topics that he often cares about. Click "Show node content" to display more information.
B. In "Author Statistics/Article Features (作者統計/文章特性)", you can see when and where each author or article is in the evolution of all knowledge, which is presented in quantitative. You can quickly know how many papers are available each year.
C. In "Similar Text Analysis (相似文本分析)", you only need to enter a certain keyword, and we will provide "Similar Keywords" and "Related Articles". We have used machine-learning techniques to provide approximate concepts, and we can also "search" by accepting words that are not exactly the same words. You can also click on similar keywords (on the right) to expand and extend relevant knowledge.
D. In "Subject cluster analysis (主題分群分析)",we use also machine learning methods to group them, so that you can know the "topics of Taiwanese Chinese research" and the direction of current popular topics and its keywords.