Artificial Intelligence and Information Mining - Collective: Workshop on Web & Graphs, Responsible Intelligence, and Social Media (WEB&GRAPH 2026)

Workshop on Web & Graphs, Responsible Intelligence, and Social Media (WEB&GRAPH 2026)

Co-located with the ACM Web Search and Data Mining (WSDM 2026), on February 26, 2026 (Boise, Idaho, USA)

Organisers

Filippo Mignosi

Univerity of L'Aquila

⚠️ Following several authors requests, we decided to extend the submission deadline from ~~November 13~~ → November 27, 2025.

Program
Accepted Papers
Aims and Scope
Important Dates
Topics of Interests
Submission and Publication
Registration and Presentation Policy
Organizers Contacts

Program

Time	Activity	Note	Duration	Session
09:00	Welcome and Opening Remarks		00:10
09:10	Keynote Speaker - Prof. Evangelos Papalexakis		00:40	SESSION 1
09:50	Minimizing the cost of Pagerank fairness	Full Paper	00:15	SESSION 1
10:05	TRuST-M: Evaluating User Trust and Explainability in LLM-Based Web Moderation Systems	Full Paper	00:15	SESSION 1
10:20	LARIS: LLM-Agent Reinforced Intervention System for Misinformation Containment on Dynamic Social Graphs	Short Paper	00:10	SESSION 1
10:30	Coffee Break		00:30
11:00	SPARK: Search Personalization via Agent-Driven Retrieval and Knowledge-sharing	Full Paper	00:15	SESSION 2
11:15	HeteroMILE: a Multi-Level Graph Representation Learning framework for Heterogeneous Graphs	Full Paper	00:15	SESSION 2
11:30	SciGraph-LLM: Automatic Knowledge Graph Construction from Scientific Papers	Full Paper	00:15	SESSION 2
11:45	WISE: Web Information Satire and Fakeness Evaluation	Full Paper	00:15	SESSION 2
12:00	Fine-Tuning or In-Context Learning? Understanding Their Trade-offs in Misinformation Detection	Short Paper	00:10	SESSION 2
12:10	GoT-TrustIoT: Graph-of-Thought Reasoning for Explainable Trust Propagation in Dynamic IoT Networks	Short Paper	00:10	SESSION 2
12:20	COFFEE: COdesign Framework for Feature Enriched Embeddings in Ads-Ranking Systems	Short Paper	00:10	SESSION 2
12:30	Local Fragments, Global Gains: Subgraph Counting using Graph Neural Networks	Short Paper	00:10	SESSION 2
12:45	Lunch		01:00
13:45	Panel Discussion		00:20
14:05	Best Paper Award		00:20
14:25	Closing Remarks		00:10

Accepted Papers

Authors	Paper Title
Shubhajit Roy, Shrutimoy Das, Binita Maity, Anant Kumar and Anirban Dasgupta	Local Fragments, Global Gains: Subgraph Counting using Graph Neural Networks
Ivan Malashin, Igor Masich, Vadim Tynchenko, Aleksei Borodulin, Andrei Gantimurov, Vladimir Nelyub and Dmitry Martysyuk	SciGraph-LLM: Automatic Knowledge Graph Construction from Scientific Papers
Han Kyul Kim, Shriniwas Nayak and Andy Skumanich	Fine-Tuning or In-Context Learning? Understanding Their Trade-offs in Misinformation Detection
Yue Zhang, Yuntian He, Saket Gurukar and Srinivasan Parthasarathy	HeteroMILE: a Multi-Level Graph Representation Learning framework for Heterogeneous Graphs
Kamalakkannan Ravi, Hemant Surale and Jiann-Shiun Yuan	TRuST-M: Evaluating User Trust and Explainability in LLM-Based Web Moderation Systems
Gaurab Chhetri, Subasish Das and Tausif Islam Chowdhury	SPARK: Search Personalization via Agent-Driven Retrieval and Knowledge-sharing
Gaurab Chhetri, Subasish Das and Tausif Islam Chowdhury	WISE: Web Information Satire and Fakeness Evaluation
Ravi Gupta, Nishant Singh, Ramya Kakarlapudi and Shiksha Patel	LARIS: LLM-Agent Reinforced Intervention System for Misinformation Containment on Dynamic Social Graphs
Ravi Gupta, Nishant Singh, Ramya Kakarlapudi and Praveen Chinapla	GoT-TrustIoT: Graph-of-Thought Reasoning for Explainable Trust Propagation in Dynamic IoT Networks
Spyridon Tzimas, Themistoklis Nikas, Evaggelia Pitoura and Panayiotis Tsaparas	Minimizing the cost of Pagerank fairness
Sohini Roychowdhury, Doris Wang, Qian Ge, Joy Mu and Srihari Reddy	COFFEE: COdesign Framework for Feature Enriched Embeddings in Ads-Ranking Systems

Aims and Scope

The Web&Graph aims to bring together researchers and practitioners from web search, data mining, artificial intelligence, and social sciences to discuss algorithmic, theoretical, and methodological advances for dynamic, reliable, and human-aligned graph analytics.

The workshop will focus on the algorithmic foundations and the applied aspects of graph reasoning for evolving networks, misinformation detection, provenance tracking, and human–AI collaboration.

Important Dates

Paper Submissions: ~~November 13~~ -> November 27, 2025.
Notifications: December 18, 2025
Workshop: February 26, 2026

All deadlines are 11:59 pm AoE.

Topics of Interests

We particularly welcome works that provide innovative and interpretable solutions or address real-world challenges by combining graphs, AI, and web algorithms. The expected, but not exhaustive, contributions are:

Theoretical Topics
- Design and analysis of graph algorithms for web and social networks
- Optimization and approximation on large and dynamic graphs
- Diffusion modeling, and algorithmic fairness
- Graph compression, sparsification, and structure-aware pruning
- Robust, explainable, and provable graph representations
Technical and Applied Topics
- Graph neural networks and graph transformers for web data
- Graph-based trust, credibility, and misinformation detection
- Influence propagation and provenance tracking for social domains
- Integration of LLMs with structured graph representations
- Human-in-the-loop knowledge-graph curation and correction
- Deep learning on dynamic and streaming graph data
- Social network analytics and algorithmic transparency
- Optimization frameworks for scalable and interpretable graph learning

Submission and Publication

We invite authors to submit unpublished, original papers written in English. Submitted papers should not have been previously published or accepted for publication in substantially similar form in any peer-reviewed venue, such as journals, conferences, or workshops. Manuscripts must be submitted in PDF according to the new ACM format published in ACM guidelines (use documentclass [sigconf,anonymous,review]{acmart}).

We will consider two different submission types:

Full papers (up to 9 pages + unlimited references) should clearly describe the state of the art and state the proposal's contribution in the application domain, even if presenting preliminary results. In particular, research papers should describe the methodology in detail, experiments should be repeatable, and a comparison with the existing approaches in the literature should be made.

Short and position papers (up to 4 pages all included) should introduce new points of view on the workshop topics or summarize a group's experience in the field.

Submissions should not exceed the indicated pages, including any diagrams and references. All submissions will undergo a double-blind review process and be reviewed by at least three reviewers based on relevance to the workshop, novelty/originality, significance, technical quality and correctness, quality and clarity of presentation, quality of references, and reproducibility. Submitted papers will be rejected without review if they are not correctly anonymized, do not comply with the template, or do not follow the above guidelines.

Generative AI Usage Policy. Generative AI models, including Chat-GPT, BARD, LLaMA, or similar LLMs, do not satisfy the criteria for authorship of papers accepted in the workshop. If authors use an LLM in any part of the paper-writing process, they assume full responsibility for all content, including checking for plagiarism and correctness of all text.

Proceedings This year, the WSDM organization will publish a Companion Proceedings Volume that includes the workshop papers.

Submission website:

Papers must be submitted through the Easychair system for this conference . Feel free to contact us should you encounter any issue.

Registration and Presentation Policy

Submitted manuscripts must adhere to the ACM authorship policy. In particular, (i) each author must be the creator or originator of an idea in the work; (ii) each author must make substantial contributions to the work; and (iii) each author must be accountable for the work that was done and its presentation in a publication. The policy was recently updated to govern the use of generative AI tools in authoring papers.

At least one author of each accepted paper must register for the conference (either 3-day or 5-day). A paper fee may be required. Please refer to the Registration policy of WSDM2026 for details.

Program Committee

We would like to express our gratitude to all members of the Program Committee, listed below:

Baek Heon, Business School of Sogang University
Boratto Ludovico, University of Cagliari
Ciccarelli Francesca, University of L’Aquila
Cinus Federico, Sapienza University of Rome
Costanzo Giuseppe, University of L’Aquila
D’Angelo Andrea, University of L’Aquila
D’Asaro Fabio, University of Salento
Du Yingpeng, Nanyang Technological University
Fossemò Daniele, University of L’Aquila
Gupta Ravi, AMD Corporation
Liu Yanming, Zhejiang University
Mignosi Filippo, University of L’Aquila
Polsinelli Matteo, University of Salerno
Raggioli Luca, University of Naples Federico II
Roychowdhury Sohini, Meta
Spezialetti Matteo, University of L’Aquila
Tzimas Spyridon, University of Ioannina

Organizers Contacts

For general inquiries about the workshop, please email matteo.spezialetti@univaq.it, andrea.dangelo6@graduate.univaq.it, francesca.ciccarelli@graduate.univaq.it, giuseppe.costanzo@graduate.univaq.it, daniele.fossemo@graduate.univaq.it