# Session 06 — Materials

Three open-access Chinese-language papers on **digital humanities** (数字人文) to load into NotebookLM during the hands-on demo. They share a theme — *how do we organize, extract, and represent knowledge in digital humanities?* — so cross-document questions land well.

## The three papers

| # | 论文 (Paper) | 期刊 / 来源 | 年份 | 公开链接 |
|---|---|---|---|---|
| 1 | 《数字人文的研究范式与平台建设》 *(Research paradigms and platform construction in DH)* | 《图书情报知识》武汉大学 | 2018 | <http://dik.whu.edu.cn/jwk3/tsqbzs/CN/article/downloadArticleFile.do?attachType=PDF&id=5728> |
| 2 | 《知识图谱在数字人文中的应用研究》 *(Knowledge graphs in digital humanities)* | 《中国图书馆学报》 | n.d. | <https://cbdb.hsites.harvard.edu/file_url/618> |
| 3 | 《数字人文中的文本挖掘研究》 *(Text mining in digital humanities)* | 北京大学中文系 | n.d. | <https://ccj.pku.edu.cn/Article/DownLoad?id=292861688&type=ArticleFile> |

All three are freely downloadable as PDFs (the URLs in the table go directly to the PDF). NotebookLM can either:

- import directly from each URL (paste the URL into **+ Add source**), or
- accept a downloaded PDF and let you re-upload.

> **Warning:** Please **verify each URL opens for you in a browser** before class. PDFs hosted on Chinese university servers occasionally move, become temporarily unavailable, or are reachable only from inside China. If any one fails, swap in one of the alternatives below.

## Alternative papers you can swap in

| 论文 (Paper) | 链接 |
|---|---|
| 《数字人文与数字出版: 分析框架及融合机制》*(DH and digital publishing: analytical framework and integration mechanisms)* | <http://dhr.ruc.edu.cn/CN/article/downloadArticleFile.do?attachType=PDF&id=137> |
| 《数字人文视角下学术名人知识模型构建研究 ——以李政道数字资源中心为例》 *(Knowledge model construction for scholars from a DH perspective — case of the Tsung-Dao Lee Digital Resource Center)* | <https://tdllib.sjtu.edu.cn/file/04-shuzirenwenshijiaoxiaxueshumingrenzhishi_yilizhengdaoshuziziyuanzhongxinweili_liuningjing.pdf> |
| 《大规模语言模型增强的中文篇章多维度阅读体验量化研究》 *(LLM-enhanced quantitative study of Chinese discourse reading experience)* | <https://aclanthology.org/2023.ccl-1.32.pdf> |

## Why these three?

The three primary picks form a **theory → method → application** progression of Chinese digital-humanities research:

1. The first paper (research paradigms) frames the **conceptual landscape** — what DH is, what platforms it needs.
2. The second (knowledge graphs) introduces a specific **knowledge-representation method** that has been central to Chinese DH for the past decade.
3. The third (text mining) introduces **computational methods** for extracting knowledge from texts.

Cross-document questions therefore land naturally: *"What methodology does each paper use?"*, *"Which framework does each paper offer for organising knowledge?"*, *"Where do the three papers disagree on what counts as 'digital humanities'?"*

You can swap any of these for a paper closer to your participants' research areas. The session's pedagogy does not depend on these specific texts — it just needs three Chinese-language DH papers that share enough thematic overlap to make cross-document RAG queries interesting.