Data and Code for the PhD Thesis "Sensing the Cultural Significance with AI for Social Inclusion"

This is the Repository of all the research data for PhD Thesis of the doctoral candidate Nan BAI from the Faculty Architecture and Built Environment at Delft University of Technology, with the title of '<em>*Sensing the Cultural Significance with AI for Social Inclusion: A Computational Spatiotemporal Network-based Framework of Heritage Knowledge Documentation using User-Generated*</em>', to be defended on October 5th, 2023.<br>Social Inclusion has been growing as a goal in heritage management. Whereas the 2011 UNESCO Recommendation on the Historic Urban Landscape (HUL) called for tools of knowledge documentation, social media already functions as a platform for online communities to actively involve themselves in heritage-related discussions. Such discussions happen both in “baseline scenarios” when people calmly share their experiences about the cities they live in or travel to, and in “activated scenarios” when radical events trigger their emotions. To organize, process, and analyse the massive unstructured multi-modal (mainly images and texts) user-generated data from social media efficiently and systematically, Artificial Intelligence (AI) is shown to be indispensable. This thesis explores the use of AI in a methodological framework to include the contribution of a larger and more diverse group of participants with user-generated data. It is an interdisciplinary study integrating methods and knowledge from heritage studies, computer science, social sciences, network science, and spatial analysis. AI models were applied, nurtured, and tested, helping to analyse the massive information content to derive the knowledge of cultural significance perceived by online communities. The framework was tested in case study cities including Venice, Paris, Suzhou, Amsterdam, and Rome for the baseline and/or activated scenarios. The AI-based methodological framework proposed in this thesis is shown to be able to collect information in cities and map the knowledge of the communities about cultural significance, fulfilling the expectation and requirement of HUL, useful and informative for future socially inclusive heritage management processes.<br>Some parts of this data are published as GitHub repositories:<br><strong style="color:rgb(86, 156, 214);">WHOSe Heritage</strong>The data of Chapter_3_Lexicon is published as https://github.com/zzbn12345/WHOSe_Heritage, which is also the Code for the Paper <em>WHOSe Heritage: Classification of UNESCO World Heritage Statements of “Outstanding Universal Value” Documents with Soft Labels</em> published in Findings of EMNLP 2021 (https://aclanthology.org/2021.findings-emnlp.34/).<br><strong style="color:rgb(86, 156, 214);">Heri Graphs</strong>The data of Chapter_4_Datasets is published as https://github.com/zzbn12345/Heri_Graphs, which is also the Code and Dataset for the Paper <em>Heri-Graphs: A Dataset Creation Framework for Multi-modal Machine Learning on Graphs of Heritage Values and Attributes with Social Media</em> published in <em>ISPRS International Journal of Geo-Information </em>showing the collection, preprocessing, and rearrangement of data related to Heritage values and attributes in three cities that have canal-related UNESCO World Heritage properties: Venice, Suzhou, and Amsterdam.<br><strong style="color:rgb(86, 156, 214);">Stones Venice</strong>The data of Chapter_5_Mapping is published as https://github.com/zzbn12345/Stones_Venice, which is also the Code and Dataset for the Paper <em>Screening the stones of Venice: Mapping social perceptions of cultural significance through graph-based semi-supervised classification</em> published in <em>ISPRS Journal of Photogrammetry and Remote Sensing</em> showing the mapping of cultural significance in the city of Venice.

本数据集库涵盖代尔夫特理工大学建筑与建成环境学院博士生Nan BAI的全部博士学位论文研究数据，论文标题为《借助人工智能感知文化意义以促进社会包容：基于用户生成数据（user-generated data）的遗产知识记录计算时空网络框架》，将于2023年10月5日进行答辩。

社会包容（Social Inclusion）已逐渐成为遗产管理领域的核心目标之一。2011年联合国教科文组织发布的《历史城市景观（Historic Urban Landscape，HUL）建议》呼吁构建知识记录工具，而社交媒体早已成为在线社群积极参与遗产相关讨论的平台。此类讨论既存在于“基线场景（baseline scenarios）”——人们平和分享其在常住或到访城市的体验，也存在于“激活场景（activated scenarios）”——重大事件触发公众情感共鸣。为高效、系统地组织、处理与分析社交媒体中海量非结构化多模态（multi-modal）（主要为图像与文本）用户生成数据，人工智能（Artificial Intelligence，AI）的作用不可或缺。

本论文探索了人工智能在方法论框架中的应用，旨在借助用户生成数据吸纳更多元群体参与遗产相关讨论。本研究属于跨学科研究（interdisciplinary study），整合了遗产研究、计算机科学、社会科学、网络科学（network science）与空间分析（spatial analysis）领域的方法与知识。研究中应用、训练与测试了人工智能模型，以分析海量信息内容，进而提取在线社群所感知的文化意义知识。研究框架在威尼斯、巴黎、苏州、阿姆斯特丹与罗马等案例城市的基线场景和/或激活场景中进行了测试。本论文提出的基于人工智能的方法论框架，能够收集城市相关信息并绘制社群对文化意义的认知图谱，契合历史城市景观（HUL）的预期与要求，可为未来社会包容型遗产管理流程提供有价值的参考依据。

本数据集的部分内容已发布至GitHub代码仓库：

**WHOSe Heritage**
第三章_词汇表（Chapter_3_Lexicon）相关数据已发布至https://github.com/zzbn12345/WHOSe_Heritage，该仓库同时也是发表于2021年自然语言处理经验方法会议（Conference on Empirical Methods in Natural Language Processing，EMNLP 2021）研究成果辑的论文《WHOSe Heritage：基于软标签的联合国教科文组织世界遗产“突出普遍价值（Outstanding Universal Value）”声明文档分类》的配套代码，论文链接为https://aclanthology.org/2021.findings-emnlp.34/。

**Heri Graphs**
第四章_数据集（Chapter_4_Datasets）相关数据已发布至https://github.com/zzbn12345/Heri_Graphs，该仓库同时也是发表于《国际摄影测量与遥感学会（International Society for Photogrammetry and Remote Sensing，ISPRS）国际地理信息期刊（ISPRS International Journal of Geo-Information）》的论文《Heri-Graphs：面向社交媒体遗产价值与属性图谱的多模态机器学习数据集构建框架》的配套代码与数据集。该论文涵盖了威尼斯、苏州与阿姆斯特丹三座拥有运河类联合国教科文组织世界遗产地城市的遗产价值与属性相关数据的收集、预处理与整理流程。

**Stones Venice**
第五章_图谱绘制（Chapter_5_Mapping）相关数据已发布至https://github.com/zzbn12345/Stones_Venice，该仓库同时也是发表于《国际摄影测量与遥感学会摄影测量与遥感期刊（ISPRS Journal of Photogrammetry and Remote Sensing）》的论文《筛选威尼斯砖石：基于图谱半监督分类绘制社会对文化意义的认知》的配套代码与数据集，该论文完成了威尼斯城市文化意义认知图谱的绘制工作。