Explainability in Web

  in Special Issue   Posted on September 28, 2020

Information for the Special Issue

Submission Deadline: Wed 28 Oct 2020
Journal Impact Factor : 1.405
Journal Name : World Wide Web
Journal Publisher:
Website for the Special Issue: https://www.springer.com/journal/11280/updates/17975196
Journal & Submission Website: https://www.springer.com/journal/11280

Special Issue Call for Papers:

Guest Editors: Guandong Xu, Hongzhi Yin, Irwin King, Lin Li

Background

This special issue encourages the submission of high-quality research papers on all topics on explainability and application topics in Web. With the aim of provision of high-quality information, services and items to users, advanced Web applications, e.g., personalisation and recommendation systems have experienced an exponential growth and advanced rapidly over the past decades. Prior efforts extensively rely on complex data mining, machine learning or latent representation models, such as association rule mining, collaborative filtering, matrix factorization, deep learning to build highly effective and accurate models to capture user preferences and profiles, however with little knowledge about the cause or explanation of predictions, and the artificial intelligent ways to achieve those results. This is mainly because on one hand, the explanation generation and explainability of such systems is far from satisfaction and generates too coarse-grained explanations, which makes the predicted outcomes less reliable and trustworthy. On the other hand, the increasing complexity of learning algorithms makes such systems working more in a black-box way, which thus sacrifices transparency, persuasiveness and satisfaction of results to end users. Providing human understandable explanations and effective explanation generation mechanism to fully address the problem of explainability, reliability, and trust has gained a high momentum in both industrial and research communities. In a broader sense, generating highly reliable explanations via advanced artificial intelligent algorithms attempts to generate both high-quality predictions and intuitive explanations for users, either in a post-hoc way or by constructing an inherently interpretable model.

Popular explainability research community has been leveraging a wide range of machine learning techniques from matrix factorization, topic modelling, graph learning, deep learning to knowledge graph embedding for generating high-quality explanations for various Web systems. Explanation generation and explainability researches are currently essential and have enhanced a diversity of real-world scenarios, such as explainable e-commerce, business intelligence, prescriptive analytics, interpretable modelling, and explainable recommendation. In order to gather and present innovative research on explainability and interpretability in Web applications, we solicit submissions of high-quality manuscripts reporting the state-of-the-art techniques and trends in this field.

Topics of interest include but are not limited to:

  • Methodology and Architectures to improve explainability
    • Interpretable machine learning
    • Intrinsically Interpretable Model
    • Model-Agnostic explainable Methods
    • Post-hoc explainable models
    • Causal analysis for explainability
    • Explainable recommender systems
    • Explainable search systems
  • Explanation generation via big data
    • Feature/sentence/word-cloud based explanations
    • Social/geo/trust-based explanations
    • Knowledge graph derived explanations
    • Multi-source data aggregation for explainability 
  • Explainable recommendation models
    • Matrix factorization models
    • Sequential based models
    • Graph and path-based models
    • Deep learning for explainable recommendations
    • Model Agnostic explainable recommendations
    • Casual learning for explainable recommendations
  • Explainable search models
    • Deep Learning models for search
    • Term explainable search
    • User behaviour analysis for explainable search
    • Feature sensitive analysis for explainable search
    • Attention mechanisms for explainable search
  • Evaluation of Explainability
    • Online/ Offline metrics
    • User studies
    • Case studies
  • Applications Trust in recommendation
    • Fairness in recommendation
    • Social/Geo-location/Group recommendation
    • Conversational recommendation
    • Web search Question & Answer
    • Chatbot & Dialogue Systems
  • Cross-disciplinary topics involving explainability
    • Casual explanation in business
    • What-if analysis and targeted marketing
    • Prescriptive analytics and intervention
    • Generating visual explanations

Important Dates

Manuscript Due: October 28, 2020
First Round of Reviews: December 20, 2020
Decision of Acceptance: February 15, 2021
Publication Date: mid 2021

Guest Editors

Guandong Xu
University of Technology Sydney, Australia
Guandong.Xu@uts.edu.au

Hongzhi Yin
The University of Queensland, Australia
h.yin1@uq.edu.au

Irwin King
Chinese University of Hong Kong, Hong Kong SAR
king@cse.cuhk.edu.hk

Lin Li
Wuhan University of Technology, China
cathylilin@whut.edu.cn

Bio

Guandong Xu is a Professor in Data Science at School of Computer Science and Advanced Analytics Institute, the University of Technology Sydney with a PhD degree in Computer Science. Guandong has had 220+ publications in the areas of Data Analytics and Data Science, Web Mining, Recommender Systems, Text Mining, Social Computing, and Predictive Analytics, including monograph books, edited conference proceedings and dozens of journal and conference papers in top venues, e.g., TNNLS, TOIS, TSE, TIST, TSC, TIFS, Inf. Sci., DSS, IEEE-IS, KAIS, IJCAI, AAAI,WWW, CVPR, ICDM, EMNLP, ICDE, CIKM, ASE etc. He is the assistant Editor-in-Chief of World Wide Web Journal and has been serving in editorial board or as guest editors for several international journals, such as Pattern Recognition, World Wide Web Journal, Social Network Analysis and Mining, the Computer Journal, Journal of Systems and Software, Online Information Review, Multimedia Tools & Applications, and Information Discovery and Delivery.

Dr. Hongzhi Yin works as a senior lecturer and an ARC DECRA Fellow (Australia Discovery Early Career Researcher Award) with The University of Queensland, Australia. He received his doctoral degree from Peking University in July 2014, and his PhD Thesis won the highly competitive Distinguished Doctor Degree Thesis Award of Peking University. His current main research interests include recommender system, social media analytics and mining, network embedding and mining, time series data and sequence data mining and learning, chatbots, federated learning, topic models, deep learning and smart transportation. He has published 130+ papers and won 5 Best Paper Awards such as ICDE’19 Best Paper Award and 21st ACM Annual Best of Computing as the main author, and most of them have been published in leading journals and top international conferences including VLDB Journal, ACM TOIS, IEEE TKDE, ACM TKDD, ACM TIST, ACM SIGMOD, ACM SIGKDD, VLDB, IEEE ICDE, AAAI, IJCAI, SIGIR, WWW, ICDM, ACM Multimedia and CIKM. He has received ARC Discovery Early Career Researcher Award (DECRA) within his first year of obtaining his PhD, ARC Discovery Project 2019 as an early-career Sole CI, UQ Foundation Research Excellence Award 2019 as the first winner of this award in School of ITEE since the establishment of this award 20 years ago. He is currently serving as Associate Editor for IEEE Journal of Social Computing and Editorial Board of Young Scientists for Journal of Computer Science and Technology (JCST).

Irwin King is a Professor at the Department of Computer Science and Engineering and the former Associate Dean (Education) and Professor, Faculty of Engineering, The Chinese University of Hong Kong. He is also the Director of Rich Media and Big Data Key Laboratory at the Shenzhen Research Institute. His research interests include machine learning, social computing, Big Data, data mining, and multimedia information processing. In these research areas, he has over 300 technical publications in journals and conferences. Prof. King is Fellow of IEEE and HKIE. He is also an Associate Editor of the Neural Network Journal and ACM Transactions on Knowledge Discovery from Data (ACM TKDD). Currently, he is President of INNS and Governing Board Member of APNNS. Moreover, he is the General Chair of WSDM2011, General Co-Chair of RecSys2013, ACML2015, the WebConf 2020, ICONIP 2020, and in various capacities in a number of top conferences such as WWW, NIPS, ICML, IJCAI, AAAI, etc.

Lin Li is a Professor in School of Computer Science and Technology, Wuhan University of Technology. Her research interest covers Data analytics, Machine learning, Information retrieval, Web personalization& Recommendation, Social media mining, Natural language processing, and so forth. She has published over 70 research papers, including over 10 journal papers and papers at top-tier conferences such as AAAI, ICDM, ICMR, etc. She serves as a reviewer for IEEE TKDE, WWWJ, KBS,KDE TOIS,TOMM and ACM TIST.

Other Special Issues on this journal

Closed Special Issues