The OCTA International Multi-Conference on “Organization of Knowledge and Advanced Technologies” is a large-scale scientific event that brings together researchers and R&D professionals focusing on ideas and common actions in the organization of knowledge. The main objective of this book is to define collaborative strategies, use advanced technologies in multiple research fields and outline applications of knowledge organization for society and its cultural, educational, economic and industrial development.

Moreover, in a collaborative way in the OCTA event, the main conjuncture between scientific and professional communities is to initiate future innovative projects, in order to bring public and private institutions closer to tomorrow’s technological challenges.

In February 2020, the scientific projects involved in the OCTA Multi-Conference edition were as follows:

– SIIE (https://siie2019.loria.fr/ & www.siie.fr) on “Information Systems and Economic Intelligence”. The SIIE international conference aims to promote dialog between experts and researchers from both public and private sectors on fundamental and experimental knowledge of Information Systems and Economic Intelligence (SIIE). Its goal is to develop technologies related to economic intelligence (EI) in a risk environment. The dynamics of EI (i.e. Competitive Intelligence) depend on mastering the knowledge and skills needed to design the best strategies and to ensure that decision-makers make the right decisions.

– ISKO-Maghreb (https://isko-maghreb2019.loria.fr/ and www.isko-maghreb.org) on “Digital Sciences: Impacts and Challenges on Knowledge Organization”. The ISKO international scholarly society is devoted to the theory and practice of organization, including the objective of the ISKO-Maghreb and the ISKO chapter in Maghreb countries, which continues to contribute to our understanding of the factors that organize knowledge and the phenomena that affect the information society. The actions to be undertaken by the scholarly society ISKO-Maghreb will have to take into account socio-cultural, cognitive and economic aspects in the strategic management of knowledge. In relation to the knowledge society, knowledge must be seen in the context of its dynamics, content and scientific and technological interactions with academics, business and politics (actors and institutions).

– CITED (https://cited2019.loria.fr/) on “Advanced Technologies, Renewable Energies and Economic Development”. The international symposium CITED aims to bring together the work on concerted and reflective research into the establishment of sustainable economic development based on technological advances, the optimal use of means and resources, and renewable energies. Joseph Aloïs Schumpeter (1934) highlighted the relationship between the innovation factor and the economic conjuncture: the pattern of economic transition, i.e. the theory of economic development. When analyzed in the context of economic cycles, the horizons of 2020–2030 appear, according to the cycles of Kondratiev (2014), as the beginning of the transition to a new era of production, industrialization and means, which can now be explained by the rise of the green economy.

– TBMS (https://tbms2019.loria.fr/) on “Big-Data-Analytics Technologies for Strategic Management: Innovation and Competitiveness”. The International Symposium TBMS explores the practical implications of Big Data and how it reconfigures relationships, expertise, methods, concepts and academic knowledge in all sectors: social, professional and economic. Today, we have more data than ever before in human history. Data volumes multiplied by 100 between 1987 and 2007, and then doubled on average every year. This is an increase infinitely greater than that caused by the invention of printing (starting with J. Gutenberg), which had resulted in a doubling of data over 50 years. In an enthusiastically transdisciplinary way, Big Data orients us towards the classification of reality into categories generated by data, instead of imposing these classifications as input at the beginning.

Taking into account transdisciplinarity, OCTA asks the following questions:

– How can we strengthen alliances between multi-disciplinary and trans-disciplinary studies?

– How can we broaden our skills surrounding common objects of study?

– How can we innovate the solutions found and propose sustainable development to society confidently?

I.1. Scientific challenges

The selected proposals, which form the OCTA edition from February 2020, mainly represent the topic of “Systems, Tools and Digital Uses for Knowledge Organization”. This scientific and multidisciplinary orientation wishes to point out the major concerns around the “Digital Uses for Knowledge Organization” with the proposals of “Models, Systems and Tools” to achieve this.

This book is a result of intensive and collaborative work between highly respected scientific authors. The nine chapters that have been selected for this book have been peer-reviewed by the OCTA program committee, both as written submissions and when presented during the OCTA multi-conference organization. In these circumstances of an exchange between authors and the scientific audience of OCTA, the proposals are enriched by authors at our request as chairs, and produce for this book an excellent reference in the “Information and Communication Sciences” and in a new scientific domain of “Digital Sciences: Impacts and Challenges on Knowledge Organization”.

I.2. Structure of this book

Chapter 1, Multi-Agent System and Ontology to Manage Ideas and Represent Knowledge: Creativity Challenge by Pedro Chávez Barrios, Davy Monticolo and Sahbi Sidhom presents and develops the implementation of an intelligent system to support idea management. This is the result of a multi-agent system (MAS) used in a distributed system with heterogeneous information as ideas and knowledge, after the results about an ontology to describe the meaning of these ideas. The authors argue that the intelligent system assists the participants of the creativity workshop to manage their ideas, thereby proposing an ontology dedicated to these ideas. During the creative workshop, many creative activities and collaborative creative methods are used by roles immersed in this creativity workshop event where they share their knowledge. The collaboration of these roles is physically distant, their interactions might be synchronous or asynchronous, and the information of ideas is heterogeneous, in order to confirm that the process is distributed. These ideas are written in natural language by participants who have a role, and are heterogeneous since some of them are described by schema, text or scenario of use. This chapter presents the MAS and the associated ontology design.

In Chapter 2, Comparative Study of Educational Process Construction Supported by an Intelligent Tutoring System by Walid Bayounes, Inès Bayoudh Sâadi and Hénda Ben Ghézala, the motivation observed by the authors is the need for educational processes that can be constructed and adapted to the needs of learners, the preferences of tutors and the requirements of system administrators and system designers of the intelligent tutoring system (ITS). In this context, this chapter explores the theory of studying the problem of educational process construction. This study introduces a new multi-level view of educational processes. Based on the proposed view, a faceted definition framework conducts a comparative study on the ITS to understand and classify issues in educational process construction.

Chapter 3, Multi-Criteria Decision-Making Recommender System Based on Users’ Reviews by Mariem Briki, Sabrine Ben Abdrabbah and Nahla Ben Amor, argues that due to the huge increase in the volume of available online data, finding relevant information becomes a very challenging task. Recommender systems (RS) achieve personalization by capturing users’ interests and provide them with items that would probably match their expectations and tastes. The objective of this chapter is to use text mining techniques to analyze users’ reviews and to detect the multi-faceted representation of the active user’s interests. The authors assume that analysis of textual data can reveal additional hidden information, allowing the profiling of users. They propose a multi-criteria text mining-based RS (MCTMRS) that defines different features/criteria of the recommended item and then builds the corpus of information of each criterion. Finally, users’ reviews are exploited to capture users’ interests in different criteria and to detect the items that satisfy users’ multi-criteria preferences. The authors tested this on a real database extracted from the TripAdvisor website. The experimental study shows that the proposed solution improves accuracy compared to traditional approaches.

Chapter 4, Spammer Detection Relying on the Reviewers’ Behaviors Features Under Uncertainty by Malika Ben Khalifa, Zied Elouedi and Eric Lefèvre, reports that nowadays the success of different companies and organizations depends on their e-reputation. The latter is manipulated by online reviews that not only have a fundamental impact on the company’s development but also deeply influence the buying decision of readers. That is why spammers post fake reviews to cheat online review systems, in order to mislead consumers and damage e-commerce. This makes spammer detection one of the most important tasks to stop fraudulent online activities and protect the e-reputation of companies, restaurants, hotels and brands. Hence, we put forward a novel approach that differentiates between spammers and innocent reviewers. The method presented by the authors is based on the K-nearest neighbor algorithm in the belief function theory and relies on suspicious behavior indicators which are considered as features. The experimental study shows the performance and robustness of the method, which was tested on two real-world labeled datasets extracted from yelp.com.

Chapter 5, Social Networking Application, Connections Between Visual Communication Systems and Personal Information on the Web by Marilou Kordahi, contributes to the field of information systems by examining the connections between social networking sites and visual communication systems. This chapter clearly presents the design of an innovative social networking application and develops a prototype of it: “SignaComm”. It enables multilingual communication between users worldwide and in various situations (e.g. protection of personal information on the Web). SignaComm is based on the theory of patterns as well as the principles of ontologies and the signage system. The theory of patterns allows the reuse of patterns to serve as assets for programming advancement and critical thinking. Ontologies define structured concepts and objects by providing significance to an information system in a particular field, and allow the development of connections between these concepts and objects. The signage system is used to provide information on a topic, in order to facilitate the communication between users on an international scale. The “signagram” is its writing unit. When creating the SignaComm, we use a machine translation of key phrases into signagrams. After writing the prototype with programming languages such as Python, PHP and Javascript, we test its capabilities to communicate instant messages to users.

Chapter 6, A New Approach of Texts and Writing Normalization for Arabic Knowledge Organization by Hammou Fadili, argues that “knowledge organization” is an important research field, as evidenced, for example, by numerous research works on classification. This last discipline is complicated, especially in the case of Arabic data from the Web, because Arabic has many forms of writing, spelling, structure, etc. on the one hand, and the lack of preprocessed and normalized data, on the other. Implementing solutions that can help remedy these problems is a real need and a big challenge for the standardization process that this language must know, especially in the new world of publishing that is the Web. This is characterized by many forms of writing styles where everyone writes in their own way without any constraints. It is in this context that the author suggests a new approach based on unsupervised deep learning methods and implements a system to help the normalization of Arabic texts and writing, in order to facilitate and improve their organization and classification.

Chapter 7, Ebola Epidemic in the Congo 2018–2019: How Does Twitter Permit the Monitoring of Rumors? by Marc Tanti, presents the Ebola epidemic that has mainly affected three West African countries (Guinea, Sierra Leone and Liberia), killing 20,000 people. A number of articles have studied the rumors that circulated during this outbreak on Twitter. For example, Fung’s article pointed out that false information about the treatment of the disease, such as bathing in salt water for healing, was disseminated on the platform (Fung 2016). Jin’s article also pointed out that these media were behind a fake news article alleging that a snake was at the origin of the epidemic. This article also listed the top 10 rumors circulating on Twitter (Jin 2014).

This study reports that the Ebola virus has been raging in the Democratic Republic of the Congo (DRC) since August 1, 2018, killing more than 2,050 people. It is the second largest epidemic after West Africa. No studies have been conducted to determine who is communicating about this epidemic and what types of tweets or rumors are being disseminated.

To answer this question, the author conducted analysis on Twitter using the Radarly® software, over a period dating from April 1 to July 7, 2019. This work has highlighted several actors communicating around the epidemic (general public, experts, politicians, the media, etc.). This study found 12 main influencers and revealed a negative message rate (rumors) of 73.31%.

Chapter 8, From Human and Social Indexing to Automatic Indexing in the Era of Big Data and Open Data by Nabil Khemiri and Sahbi Sidhom, outlines that in the era of Big Data and Open Data, massive and heterogeneous collections of documents (from text to multimedia) are created, managed and stored electronically. To make these documents more usable, a set of processes, like human (i.e. manual) indexing, social indexing and automatic (i.e. machine/algorithmic) indexing, make it possible to create representations of documents by a set of metadata, descriptors (or terms) and social tags. These representations will make it easier to find information in a massive and scalable collection of documents from different sources (document databases, social networks, Open Data, etc.), in order to respond to user information needs (i.e. user requests). Numerous research studies have been carried out to put forward indexing approaches depending on the type of indexed documents, as well as to observe the evolution of indexing methods linked to the evolution of document representations, electronic content, Big Data and Open Data. This chapter presents a detailed overview, including a state of the art on approaches and methodologies from human/manual indexing, social indexing and automatic indexing with a set of algorithmic methods in the era of Big Data and Open Data.

Chapter 9, Strategies for the Sustainable Use of Digital Technology by the AWI in the Management of Knowledge and Cultural Communication on the “Arab World” by Asma Abbassi, shows that today more than ever, in the post-digital era, the management, production and transmission of content face major and multiple challenges. The stakes become all the greater when this content, which is seen, read and listened to, conditions knowledge and scholarship around a civilization or a geographical area. Such is the case with the Arab World Institute (AWI). Similarly, knowledge management and cultural communication have a special place in sustainable development, which has become a concept of primary interest in global policies for several years (CGLU 2015). The optimization of cultural tools has now become a necessity and even an emergency. This chapter lies in this context, as it is part of a several-year doctoral work focused on the study of the images of the “Arab world” produced by the AWI via its public activities. It is also based on a recent work that analyzes the digital communication strategy of the AWI and its digital media.

At the crossroads of digital humanities, cultural studies and information, communication sciences and sustainable development, the author suggests studying the relationships between the material and immaterial worlds and the management methods of knowledge through various digital tools, the images conveyed around the “Arab world” via the construction, organization and transmission of knowledge from the AWI. This study integrates the feedback issue and the degree of interaction of audiences, mainly those in the “Arab world”, with a discussion on digital sustainability and durable knowledge management.

I.3. References