# Using Web Data for Global Insights: An Introduction to webAI #### calendar\_today Date and Time **May 16, 2025** 09:00AM - 03:00PM EDT #### pin\_drop Location **CGIS** [Knafel K354 Cambridge, MA 02138 United States ]() **Instructors** - [Dr. Jan Kinne](https://www.linkedin.com/in/jan-kinne/?originalSubdomain=de) - [Robert Dehghan](https://www.linkedin.com/in/robertdehghan/) - [Sebastian Schmidt ](https://www.linkedin.com/in/sebastian-schmidt-a4688b153/)(Istari.ai) - [Devika Jain](https://gis.harvard.edu/gis.harvard.edu/people/devika-kakkar) (Harvard CGA) ## **Mode** Full-day, on-site workshop with limited capacity (maximum of 30-40 participants) ## **Description** This workshop introduces[ ISTARI ](https://www.istari.ai/)webAI, a data platform that helps researchers explore global economic, technological, and social trends using publicly available online information. Based on data from 40 million organizations worldwide, webAI turns unstructured web content into structured indicators, time series, and network data. In the morning session, we will explain the core ideas behind webAI: how it collects and processes data, how indicators are built, and how these have already been used in studies on topics such as innovation, sustainability, and regional development. We will also discuss the strengths and limitations of using web data for research.The afternoon will be hands-on. Participants will work with both the interactive webAI Platform and curated datasets to explore real-world cases. This includes selecting and analyzing organizations globally, running time-based and geographic analyses, and working with network data. The workshop is open to researchers from all fields interested in new data sources and digital methods. All participants will receive access to the webAI Platform for continued use after the event. ## **Morning Schedule (9:00 AM – 12:00 PM)** ### **Session 1: Foundations of webAI – Concept, Data, and Methodology** ### *Presenter: Dr. Jan Kinne* Description: In this session, Jan introduces the scientific foundations of ISTARI webAI. He explains how publicly available web data is processed, how organizations are identified and analyzed, and how structured indicators, time series, and network data are generated. The session also covers key methodological choices and challenges working with large-scale web data. ### **Session 2: Practical Applications – Use Cases from Public and Business Sectors** *Presenter: Robert Dehghan* Description: Robert presents real-world applications of webAI in both public policy and private sector contexts. Covering a broad range of topics—from innovation monitoring and regional development to competitive intelligence and technology scouting—this session shows how webAI insights are being used to support data-driven decision-making. ### **Session 3: Research with webAI – Geographic Analysis and Sustainability** *Presenter: Sebastian Schmidt* Description: Sebastian presents selected scientific studies conducted with webAI data, with a special focus on spatial analysis and sustainability-related topics. He demonstrates how web-based indicators can be combined with geospatial data to explore regional patterns and trends in areas such as green innovation and technology diffusion. ## **Afternoon Schedule (1:00 PM – 5:00 PM)** ### **Session 4: Exploring Organizations and Topics with the webAI Platform** *Presenter: Dr. Jan Kinne, Robert Dehghan, Sebastian Schmidt* Description: In this hands-on session, participants will work directly with the webAI platform. The session demonstrates how to explore any topic of interest by identifying and analyzing relevant organizations worldwide based on their digital footprint. Participants will learn how to search, filter, and generate insights in real time using interactive features of the platform. The goal is to empower researchers to independently discover trends and structures from web-based data. ### **Session 5: Working with Large-Scale Web-Based Datasets** *Presenter: Dr. Jan Kinne, Robert Dehghan, Sebastian Schmidt* Description: This session focuses on the use of precompiled, large-scale datasets derived from webAI. Participants will follow structured workflows to perform temporal, geospatial and network. Key examples include time series analysis of organizational change, geographic distribution of thematic clusters, and network mapping of inter-organizational links. The session highlights the potential of web-based data for quantitative research across various domains. ### **Session 6: Collaboration with Harvard Center for Geographic Analysis** *Presenter: Devika Jain* Description: This session will highlight the collaboration between Istari.ai and the Harvard Center for Geographic Analysis (CGA), and provide guidance on how Harvard users can access and utilize the Istari.ai platform. Attendees will learn how to request a license for self-guided exploration, as well as how to request pre-processed datasets. The session will also showcase select use cases demonstrating the platform’s capabilities for advanced geospatial analysis. ## **Learning Objectives** - Gain an introduction to webAI as a scalable method for analyzing global organizations and trends using web data. - Explore real-world applications of webAI in public policy, business intelligence, environmental science, and regional development. - Examine academic case studies focused on innovation, sustainability, and geographic patterns. - Participate in an interactive session with the Istari.ai webAI platform to explore custom topics and generate insights in real time. - Engage in hands-on analysis of large-scale datasets, including time series, spatial distributions, and network structures. - Learn how to apply the Istari.ai platform for advanced geospatial data science and GeoAI research. ### **Target Audience** This workshop is intended for anyone currently using—or planning to use—web-based AI in their research. It is especially relevant for researchers in AI, Data Science, Geospatial Science, Social Sciences, Economics, Technology, and Environmental Studies. ### **Expected Prerequisites** None. Just bring your own laptop and laptop charger. ### **To Attend** The workshop is **free** for individuals with a valid Harvard ID. Please click on the green button below to register. A video version of the workshop will be made publicly available a few days later for those unable to attend in person. ### [HARVARD APPLY](https://projects.iq.harvard.edu/cga-pin/registration-cga-training) **Contact** For any questions regarding the workshop, please email [Devika Jain](https://gis.harvard.edu/gis.harvard.edu/people/devika-kakkar) at . A slack channel for questions and assistance will also be created prior to the event. See also:- [ Workshops, Seminars & Classes ](/event-type/workshops-seminars-classes) - [ Center for Geographic Analysis ](/program/center-geographic-analysis) - [ GIS ](/research-technology/gis) Share on:- [ Facebook ](#) - [ Twitter ](#) - [ Linkedin ](#) Save: [ Add to calendar calendar\_today ](https://www.iq.harvard.edu/node/1954886/event-feed.ics) Copy link link