WHAC2026

 Call For Papers

WHAC26 proposes a data challenge focused on developing computational models to understand the long-term resilience of human societies to environmental change. We provide a novel assembled dataset combining cultural evolution variables about past societies (population, crises, cultural evolution proxies, secular cycle phases etc.) with paleoclimate proxies (temperature and relative growth trend per continent) and challenge communities working in social computing, cultural evolution, Natural Language Processing and Cliodynamics in two tasks:

Task 1: predict the secular cycle phase of societies from the shared dataset (evaluate it with Spearman correlation), 

Task 2: modeling patterns of cultural evolution and climate resilience from the shared data (also integrated with your own data)

The data challenge format will allow the comparison of different approaches and findings. We welcome Abstracts (2 pages including references). Selected works will be required to provide a short paper (6 pages plus 2 for references) that will be published in the conference proceedings. The Programme Committee will select the best papers and write a summary paper. Authors should use the LNCS template available on Overleaf, Word, LaTeX. Papers can address just one or both the tasks. Participants are allowed to add any other resource or dataset, and apply any methodology available to perform the tasks, but we require the use of the provided dataset.

for questions to organizers write to fabio.celli@maggioli.it

Important Dates

Abstract (2 pages) Submission: 23 January 2026

Short papers (6 pages) Submission: 16 February 2026

Notification of acceptance: 23 March 2026

Camera-ready papers: 10 April 2026

Author registration period: 23 March – 10 April 2026

Non-author registration (in-person only): 23 March – 1 June 2026

Workshop sessions: 29 June – 1 July 2026 (exact date and time will be communicated)

  Prize

The paper with the best system performing task 1 will be selected for pubblication in the Journal of Computer Science (Impact Factor: 3.7)