ML-SDA 2022
Special Session on Machine Learning for Social Data Analytics
at the 14th International Conference on Computational Collective Intelligence (ICCCI 2022)Hammamet, Tunisia, September 28-30, 2022
Conference website: http://www.iccci.pwr.edu.pl
Special Session Organizers
Salma Jamoussi
Higher Institute of Computer Sciences and Multimedia of Sfax
University of Sfax, Tunisia
E-mail: salma.jammoussi@isims.usf.tn
Hanen Ameur
Multimedia, InfoRmation Systems and Advanced Computing Laboratory
University of Sfax, Tunisia
E-mail: ameurhanen@gmail.com
Hasna Njah
Higher Institute of Computer Sciences and Multimedia of Gabes
University of Gabes, Tunisia
E-mail: njah.hasna@isimg.tn
Higher Institute of Computer Sciences and Multimedia of Sfax
University of Sfax, Tunisia
E-mail: salma.jammoussi@isims.usf.tn
Hanen Ameur
Multimedia, InfoRmation Systems and Advanced Computing Laboratory
University of Sfax, Tunisia
E-mail: ameurhanen@gmail.com
Hasna Njah
Higher Institute of Computer Sciences and Multimedia of Gabes
University of Gabes, Tunisia
E-mail: njah.hasna@isimg.tn
Objectives and topics
Nowadays, social networks play a crucial role in every aspect of our daily life. They are seen as huge data mines that attract researchers to tackle several challenges. Ranging from predicting users simple reactions to representing more complex personality features, mining social data clear the way for promising applications that significantly impact our real-life.
Meanwhile, machine learning methods, characterized by recent breakthroughs of Deep Learning and Big Data, yield ultrapractical models dealing with data analytics. Following these advancements, text processing for example, has never been as intuitive as it is today. Particularly, embedding data, as dense vectors, ensures faithful representations of the text content making it possible to use the wide spectrum of machine learning methods for social data analytics. Analogically, mining other social data types (image, video, reactions, etc.) and layouts (graph, time series, sequential, etc.) has known remarkable success owing to the recent developments in machine learning methods.
Following this context, the aim of the ML-SDA 2022 session is to bring together scientists, researchers, engineers, and practitioners to present and to discuss recent and innovative research papers that address the breakthroughs of machine learning in social data analytics. It focuses on new methods, models and applications that use machine learning to process social data and namely to extract useful knowledge from it. The ML-SDA 2022 topics of interest deal with, but are not limited to, the use of different types of machine learning methods for:
Meanwhile, machine learning methods, characterized by recent breakthroughs of Deep Learning and Big Data, yield ultrapractical models dealing with data analytics. Following these advancements, text processing for example, has never been as intuitive as it is today. Particularly, embedding data, as dense vectors, ensures faithful representations of the text content making it possible to use the wide spectrum of machine learning methods for social data analytics. Analogically, mining other social data types (image, video, reactions, etc.) and layouts (graph, time series, sequential, etc.) has known remarkable success owing to the recent developments in machine learning methods.
Following this context, the aim of the ML-SDA 2022 session is to bring together scientists, researchers, engineers, and practitioners to present and to discuss recent and innovative research papers that address the breakthroughs of machine learning in social data analytics. It focuses on new methods, models and applications that use machine learning to process social data and namely to extract useful knowledge from it. The ML-SDA 2022 topics of interest deal with, but are not limited to, the use of different types of machine learning methods for:
- Sentiment and opinion mining
- Emotion detection
- Hate speech analysis
- Streaming data processing
- Multilingual content processing
- Hot Topic detection and tracking
- Abnormal and fake content identification
- Irony and sarcasm detection
- User behavior modeling and prediction
- Link prediction
- Community detection
- Opinion evolution modeling
- Social influence modeling
- Popularity prediction
- User Profiling from social data
- Recommendation systems using social data