Information Processing & Management is devoted to refereed reporting of:

1. Basic and applied research in information science, computer science, cognitive science and related areas that deals with: the generation, representation, organization, storage, retrieval, and use of information; the nature, manifestations, behavior, and effects of information and knowledge; communication and distribution of information and knowledge; and human information behavior.

2. Experimental and advanced processes, related to: information retrieval (IR); digital libraries; knowledge organization and distribution; digitized contents - text, image, sound and multimedia processing; and human-computer interfaces in information systems. Implementations in information retrieval systems and a variety of information systems, networks, and contexts. Related evaluation.

3. Management of information resources, services, systems and networks, and digital libraries. Related studies of the economics of information and the principles of information management.

The aim is to provide an international forum for advanced works and critical analysis in these interdependent and interdisciplinary areas. Invited are original papers and critical reviews of trends reporting on:
• Progress in the theory, principles, and procedures in information processing, particularly involving information retrieval; search engines; knowledge and distributed intelligence; information representation, classification, extraction, filtering and summarization; question answering; information navigation, browsing and visualization; and human-computer interaction in information systems.
• Research on the formal characteristics and properties of information and knowledge and the associated processes of communication among humans and between humans and machines. Includes studies of human information needs, seeking, searching, and use; and bibliometric and infometric studies of the structural and statistical properties of information artifacts.
• Modeling and evaluation of information systems performance, particularly of information retrieval systems, knowledge systems, and digital libraries. Studies of their effectiveness, efficiency, value, or impact.
• Studies in management and economics of information and information systems. Use of information for decision making and problem solving.
• Studies in information policies. Data and issues relevant to information policies on organizational, national, and international levels. Derivation and use of information indicators.

Special Issue on Explainable AI (XAI) for Web-based Information Processing
Submission Date: 2020-09-30

The Web has become a ubiquitous tool for finding/sharing information, and conducting business, learning and entertainment. Web intelligence (WI) strives to develop innovative solutions and frameworks that deepen the understanding of computational, logical, cognitive, physical, and social foundations of the future web. An intelligent web is one capable of making sense in an equivalent way to how humans do. The Sentiment Web, the Sentient-Sensory Web, the Synergistic Web and the Solution-Savvy Web collectively lead to the intelligence of “Web”. Typical applications of WI such as online text classification, Web document clustering, web recommender for e-commerce, web usage profiling and similar knowledge discovery tasks are drawing attention from communities of global researchers. The knowledge-intensive and intelligent service web generates substantial amount of data that often contains complex attributes. Moreover, it is unstructured and is generated asynchronically, dynamically from web activities, for example the web usage data. To deal with the big data which is essential to web intelligence and the related applications, advanced analytics and machine learning algorithms are vital for supporting knowledge discovery.

Artificial intelligence (AI) driven models, especially deep learning models have achieved state-of-the-art results for various natural language processing, data analytics and pattern recognition tasks. Undeniably, WI presents excellent opportunities and challenges for the research and development of new generation web-based information processing technology as well as for exploiting business intelligence and AI, especially machine learning can optimize this dynamically changing and unpredictable task environment. We get highly accurate predictions using these in conjunction with large datasets, but with little understanding of the internal features and representations of the data that a model uses for information processing and data analytics. The techniques lack explanations and reasons for how and why a decision has been made. Basically, these perfect black-box machine learning techniques lack transparency and explainability. Explainable AI (XAI) is an emerging field in machine learning that aims to address how black box decisions of AI systems are made. It refers to methods and techniques in the application of AI technology such that the results of the solution can be understood by human experts. For creating human-comprehensible interpretations, it is crucial to create an equilibrium, as the common belief is that a negative relationship exists between the performance of a model and its explainability. XAI solutions will enable improved prediction accuracy with decision understanding and traceability of actions taken and have even more impact in the business/research or decision making. It aims to improve human understanding, determine the justifiability of the decision made by the machine, introduces trust and reduces bias.

The special issue aims to stimulate discussion on the design, use and evaluation of XAI models as the key knowledge-discovery drivers to recognize, interpret and process information within the socially connected ecosystem. We invite theoretical work and review articles on practical use-cases of XAI that discuss adding a layer of interpretability and trust to powerful algorithms such as neural networks, ensemble methods including random forests for delivering near real-time intelligence. Full length, original and unpublished research papers based on theoretical or experimental contributions related to understanding, visualizing and interpreting deep learning models for new generation webbased information processing technology and interpretable machine learning for exploiting business intelligence are welcome.

The list of possible topics includes, but is not limited to:  

XAI for web intelligence data
Ante-hoc and post-hoc explainability techniques for AI models
Reasoning Web using XAI
Web Mining using Human-understandable AI systems
Interpretable adversarial learning for WI applications
Explainable Deep Bayesian learning for WI applications
Intelligent feature selection for interpretable web analytics
Semantic Web and XAI
Social network analysis using XAI
Web security, integrity, privacy and trust using XAI
Linguistic knowledge of deep neural networks for text mining
Natural language processing and XAI
Knowledge representation methods for online opinions
Explaining online predictions and recommendations
Interpretable multi-view representation learning for fusing disparate web data sources
Opinion spamming and intent mining using Human-understandable AI systems
Trust and interpretability in web data classification
XAI methods for Web of Things (WoT) data

Special Issue on Creative Language Processing
Submission Date: 2020-10-31

 Aims and scope

The SI focuses on topics deepening the knowledge on the creative use of language. Instead of taking up basic topics from the fields of CL and NLP, such as improvement of part-of-speech tagging, we will promote research focused on such creative topics as humor processing, deceptive language processing, figurative language processing, and others for which the generally perceived state-of-the-art has not been established yet.

Target audience

The SI is addressed at the audience comprised of scientists, researchers, scholars, students and practitioners performing research in the analysis or generation of language, with a specific weight put on studies focused on the creative use of language, and the creative methods for the processing of language. The Special Issue will not accept research on basic topics for which the field has been well established, such as improvement of part-of-speech tagging, etc., unless they directly contribute to the idea of creative processing of language phenomena.

List of Topics

The Special Issue will invite papers on topics listed, but not limited to the following:

l natural language processingl computational linguisticsl creative language processingl figurative language processingl NLP applicationsl natural language generationl emotional language processingl humor and joke processingl deceptive language detectionl emoticon processingl automatic cyberbullying detectionl fake news detectionl abusive language processingl story generationl poetry generation

Special Issue on Algorithmic Bias and Fairness in Search and Recommendation
Submission Date: 2020-11-15

Search and recommendation algorithms are playing a primary role in supporting individuals at filtering the overwhelming alternatives our daily life offers. Such an automated intelligence is being used on a myriad of platforms covering different domains, from e-commerce to education, from healthcare to social media, and so on. The ongoing research in these fields is posing search and recommendation algorithms closer and closer, with search algorithms being personalized based on users' characteristics, and recommendaton algorithms being optimized on the ranking quality. This attitude results in enabling the identification of common challenges and shared priorities, essential to tailor these systems on the needs of our society.

Over the aspects getting special attention in search and recommendation so far, the capability to uncover, characterize, and counteract data and algorithmic biases, while preserving the original level of accuracy, is proving to be prominent and timely. Both classes of algorithms are trained on historical data, which often conveys imbalances and inequalities. Such patterns in the training data might be captured and emphasized in the results these algorithms provide to users, leading to biased or even unfair decisions. This can happen when an algorithm systematically discriminates users as individuals or as belonging to a legally-protected class, identified by common sensitive attributes.

Given the increasing adoption of systems empowered with search and recommendation capabilities, it is crucial to ensure that their decisions do not lead to biased or even discriminatory outcomes. Controlling the effects generated by popularity bias to improve the user's perceived quality of the results, supporting consumers and providers with fair rankings and recommendations, and providing transparent results are examples of challenges that require attention. This special issue intends to bring together original research methods and applications that put people first, inspect social and ethical impacts, and uplift the public’s trust on search and recommendation technologies. The goal is to favor a community-wide dialogue on new research perspectives in this field.

We solicit different types of contributions (research papers, surveys, replicability and reproducibility studies, resource papers, systematic review articles) on algorithmic bias in search and recommendation, focused but not limited to the following areas. If in doubt about the suitability, please contact the Guest Editors.

Data Set Collection and Preparation:

Managing imbalances and inequalities within data sets
Devising collection pipelines that lead to fair and unbiased data sets
Collecting data sets useful for studying potential biased and unfair situations
Designing procedures for creating synthetic data sets for research on bias and fairness

Countermeasure Design and Development:

Conducting exploratory analysis that uncover biases
Designing treatments that mitigate biases (e.g., popularity bias mitigation)
Devising interpretable search and recommendation models
Providing treatment procedures whose outcomes are easily interpretable
Balancing inequalities among different groups of users or stakeholders

Evaluation Protocol and Metric Formulation:

Conducting quantitative experimental studies on bias and unfairness
Defining objective metrics that consider fairness and/or bias
Formulating bias-aware protocols to evaluate existing algorithms
Evaluating existing strategies in unexplored domains
Comparative studies of existing evaluation protocols and strategies

Case Study Exploration:

E-commerce platforms
Educational environments
Entertainment websites
Healthcare systems
Social media
News platforms
Digital libraries
Job portals
Dating platforms

Special Issue on Dis/Misinformation Mining from Social Media
Submission Date: 2021-01-20

We solicit original, unpublished and innovative research work on all aspects around, but not limited to, the following themes:

Descriptive models on fake new and malicious bot detection.
Explainable AI for detection of dis/misinformation.
User behavior analysis and susceptibility prediction with regard to dis/misinformation in social media.
Trust and reputation in social media.
Dis/misinformation propagation modeling and trace analysis.
Prescriptive countermeasure methods against formation and circulation of misinformation
Predicting misinformation and bias in news on social media.
Predictive models for early detection of hoax spread in social media.
Social influence analysis on online social media including discovering influential users and social influence maximization.
Assessing the influence of fake news on advertising and viral marketing in social media.
New datasets and evaluation methodologies to help predicting dis/misinformation in social media
User modeling and social media including predicting daily activities, recurring events Determining user similarities, trustworthiness and reliability.
Social media and information/knowledge dissemination such as topic and trend prediction, prediction of information diffusion patterns, and identification of causality and correlation between events/topics/communities.
Merging internal (proprietary) data with social data.