Systems and Uses of Digital Sciences for Knowledge Organization

Sahbi Sidhom is Full Professor at the University of Lorraine, France, and Senior Researcher affiliated with the Lorraine Research Laboratory in Computer Science and its Applications, a research unit that is shared by CNRS, the University of Lorraine and INRIA Grand-Est. His research focuses on knowledge organization, information processing with NLP and data mining and web intelligence systems.Amira Kaddour is a Professor at the University of Carthage, Tunisia, and is the Chair of the professional master’s degree on “Innovation Engineering and Technology Transfer” at ENSTAB Engineering School. Her research focuses on financial risk management, economy and financial modeling and data financial intelligence.

• Introduction xiSahbi SIDHOM and Amira KADDOURChapter 1 Multi-Agent System and Ontology to Manage Ideas and Represent Knowledge: Creativity Challenge 1Pedro Chávez BARRIOS, Davy MONTICOLO and Sahbi SIDHOM1.1 Introduction 11.2 Multi-agent system (MAS) and ontology 31.2.1 MAS and ontology 31.2.2 MAS methodologies 51.2.3 Methodologies to design ontologies 61.3 MAS and ontology: our approach proposal 71.3.1 MAS methodology GAIA 71.3.2 Applying the ontology, Uschold’s ontology 81.4 Results 91.4.1 Multi-agent system results 91.4.2 Ontology results 131.5 Conclusion 161.6 Appendices 161.7 References 22Chapter 2 Comparative Study of Educational Process Construction Supported by an Intelligent Tutoring System 27Walid BAYOUNES, Inès BAYOUDH SÂADI and Hénda BEN GHÉZALA2.1 Introduction 272.2 New view of educational process 282.2.1 Psycho-pedagogical level 302.2.2 Didactic level 302.2.3 Situational level 302.2.4 Online level 302.3 Definition framework 302.3.1 Didactic domain world 312.3.2 Instructional design world 322.3.3 Learning environment world 332.3.4 Learning situation world 342.4 Comparative study 342.4.1 Study scope 342.4.2 Description of systems 352.4.3 Specification of approaches 362.4.4 Study results and discussion 502.5 Conclusion and future works 512.6 References 52Chapter 3 Multi-Criteria Decision-Making Recommender System Based on Users’ Reviews 55Mariem BRIKI, Sabrine BEN ABDRABBAH and Nahla BEN AMOR3.1 Introduction 553.2 Multi-criteria decision-making 563.3 Basics of recommendation systems and related work 583.3.1 Recommender systems 583.3.2 Text mining-based recommendation systems 593.3.3 Multi-criteria recommender systems 603.4 New multi-criteria text-based recommendation system 623.4.1 Primary criterion-based recommendation system 623.4.2 Multi-criteria text mining-based recommendation system 663.5 Experimental study 673.5.1 Dataset and metrics 673.5.2 Evaluation metrics 683.5.3 Experimental protocol 693.5.4 Experimental results 703.6 Conclusion 713.7 References 72Chapter 4 Spammer Detection Relying on Reviewer Behavior Features Under Uncertainty 75Malika BEN KHALIFA, Zied ELOUEDI and Eric LEFÈVRE4.1 Introduction 754.2 Background 784.2.1 The belief function theory 784.2.2 Evidential K-nearest neighbors 804.3 Spammer detection relying on the reviewers’ behavioral features 814.3.1 Step 1: Features extraction 824.3.2 Step 2: Initialization and learning phase 874.3.3 Step 3: Distinguishing between innocent and spammer reviewers 884.4 Experimental study 894.4.1 Evaluation protocol 904.4.2 Results and discussion 914.5 Conclusion and future work 924.6 References 92Chapter 5 Social Networking Application, Connections Between Visual Communication Systems and Personal Information on the Web 97Marilou KORDAHI5.1 Introduction 975.2 Related published works 1005.3 Pattern for the SignaComm, first approach 1015.3.1 SignaComm’s context 1025.3.2 SignaComm’s pattern 1035.4 From text phrases to signagrams for the protection of personal data 1075.4.1 Automatic translation 1075.4.2 Dictionary of signagrams 1095.5 SignaComm’s first technical test 1105.5.1 Interface pattern 1105.5.2 User profile pattern 1115.5.3 Machine translation pattern 1115.5.4 Activity pattern 1135.6 Discussion and conclusion 1135.7 Acknowledgment 1145.8 References 114Chapter 6 A New Approach of Texts and Writing Normalization for Arabic Knowledge Organization 119Hammou FADILI6.1 Introduction 1196.2 Motivation 1206.3 Using a machine learning model 1206.4 Technological elements integration 1246.5 Corpus and dataset 1266.6 Experiences and evaluations 1276.6.1 Results 1296.7 Conclusion 1306.8 References 131Chapter 7 Ebola Epidemic in the Congo 2018–2019: How Does Twitter Permit the Monitoring of Rumors? 137Marc TANTI7.1 Introduction 1377.2 Materials and methods 1397.3 Results 1437.3.1 Regarding the general public, the citizens 1437.3.2 Regarding the experts 1457.3.3 Regarding the media 1467.3.4 Regarding the politicians 1487.4 Conclusion 1497.5 Acknowledgment 1507.6 References 150Chapter 8 From Human and Social Indexing to Automatic Indexing in the Era of Big Data and Open Data 153Nabil KHEMIRI and Sahbi SIDHOM8.1 Introduction 1538.2 Indexing definition 1548.3 Manual indexing 1558.4 Automatic indexing 1568.4.1 Statistical indexing methods 1568.4.2 Linguistic indexing methods 1578.4.3 Semantic indexing 1588.4.4 Social indexing 1598.5 Indexing methods for Big Data and Open Data 1598.6 Conclusion 1618.7 References 161Chapter 9 Strategies for the Sustainable Use of Digital Technology by the AWI in the Management of Knowledge and Cultural Communication on the “Arab World” 165Asma ABBASSI9.1 Introduction 1659.2 The Arab World Institute and the construction of knowledge around the “Arab World” in the West 1669.3 The AWI’s digital communication strategies 1689.4 The images built by the AWI and the question of feedback 1769.5 The role of digital tools in sustainability and durability in the management of knowledge and communication at the AWI 1789.6 Conclusion 1809.7 References 181List of Authors 185Index 187