Aim and Scope

A huge amount of information is nowadays available in the form of texts and documents generated by heterogeneous sources. These sources include online social networks, news websites, clinical and industrial report repositories, digital libraries, and massive open online courses. This wealth of textual information offers unprecedented opportunities for extracting valuable knowledge that can be exploited in a wide range of application domains, such as decision support, event detection and forecasting, user and customer profiling, marketing strategies, sentiment analysis, opinion mining, and text summarization.

In recent years, text and document mining have attracted increasing attention from the scientific community. Significant advances have been achieved through approaches based on data mining, machine learning, artificial intelligence, and statistics, with a growing impact of neural models, deep learning techniques, and language models for text representation and understanding. In parallel, several commercial platforms for large-scale text analytics have been developed. Nevertheless, the analysis of streams of text and documents still presents a number of open challenges. These challenges include the need for scalable and online processing techniques, the unstructured nature of textual data, and the presence of concept drift, where the underlying phenomena evolve over time and may lead to performance degradation of machine learning models.

The aim of this special session is to provide a forum for researchers and practitioners from both academia and industry to present and discuss recent advances, novel methodologies, and practical solutions for extracting actionable knowledge from streams of text and documents. The session welcomes contributions that advance the state of the art in designing intelligent systems capable of handling the unstructured nature of textual data while maintaining long-term performance in continuously evolving environments.

Potential topics of interest include but are not limited to:

• Concept Drift Detection in Text and Document Classification and Clustering

• Incremental and Online Learning of models for Text and Document Mining

• Neural Models and Deep Learning for Streaming Text Data

• Explainable and Interpretable Models for Text Stream Mining

• Text and Document Categorization

• Text and Document Summarization

• Fake News Detection and Misinformation Analysis

• Consensus and Conflict Analysis from Multi-Source Text Streams

• Sentiment Analysis and Opinion Mining

• Social Sensing from Textual Data

• Scientific Document Analysis

• Community Discovery from Textual Sources

• Event Detections from Textual Sources

• Crawling and Scraping Solutions for Streams of Texts and Documents

• Benchmarking, Datasets, and Evaluation Protocols for Text Streams

• Industrial Applications of Text Stream Mining Systems

 Important Dates

• Paper Submission: March 15, 2026

• Decision Notification: May 15, 2026

• Camera Ready Submission: June 15, 2026

Organizers

The papers accepted for the special session will be included in the IEEE EAIS 2026 proceedings and will be published by the IEEE Xplore Digital Library. Submission instructions can be found here: 

https://ai.dii.unipi.it/eais-2026-submission/

More details on IEEE EAIS 2026 event can be found at:

https://ai.dii.unipi.it/eais2026/