Knowledge Needs and Information Extraction

Nicolas Turenne is a researcher at INRA in the Science and Society team at the University of Paris-Est Marne la Vallée in France. He specializes in knowledge extraction from texts with theoretical research into relational and stochastic models. His research topics also concern the sociology of uses, food and environmental sciences, and bioinformatics.

• Introduction xiAcknowledgements  xiiiChapter 1. Consciousness: an Ancient and Current Topic of Study 11.1. Multidisciplinarity of the subject 11.2. Terminological outlook 21.3. Theological point of view 41.4. Notion of belief and autonomy 51.5. Scientific schools of thought 61.6. The question of experience 7Chapter 2. Self-motivation on a Daily Basis 92.1. In news blogs 92.2. Marketing 92.3. Appearance 102.4. Mystical experiences 112.5. Infantheism 112.6. Addiction 11Chapter 3. The Notion of Need 153.1. Hierarchy of needs 153.1.1. Level-1 needs 163.1.2. Level-3 needs 173.2. The satiation cycle 18Chapter 4. The Models of Social Organization 214.1. The entrepreneurial model 214.2. Motivational and ethical states 23Chapter 5. Self Theories 29Chapter 6. Theories of Motivation in Psychology 336.1. Behavior and cognition 336.2. Theory of self-efficacy 346.3. Theory of self-determination 386.4. Theory of control 396.5. Attribution theory 396.6. Standards and self-regulation 426.7. Deviance and pathology 476.8. Temporal Motivation Theory 486.9. Effect of objectives 496.10. Context of distance learning 496.11. Maintenance model 496.12. Effect of narrative 496.13. Effect of eviction 506.14. Effect of the teacher–student relationship 506.15. Model of persistence and change 506.16. Effect of the man–machine relationship 51Chapter 7. Theories of Motivation in Neurosciences  537.1. Academic literature on the subject 537.2. Psychology and Neurosciences 537.3. Neurophysiological theory 547.4. Relationship between the motivational system and the emotions 567.5. Relationship between the motivational system and language 587.6. Relationship between the motivational system and need 59Chapter 8. Language Modeling  618.1. Issues surrounding language 618.2. Interaction and language 618.3. Development and language 628.4. Schools of thought in linguistic sciences 628.5. Semantics and combination 688.6. Functional grammar 688.7. Meaning-Text Theory 698.8. Generative lexicon 708.9. Theory of synergetic linguistics 708.10. Integrative approach to language processing 718.11. New spaces for date production 738.12. Notion of ontology 758.13. Knowledge representation 76Chapter 9. Computational Modeling of Motivation 819.1. Notion of a computational model 819.2. Multi-agent systems 819.3. Artificial self-organization 859.4. Artificial neural networks 879.5. Free will theorem 889.6. The probabilistic utility model 899.7. The autoepistemic model 91Chapter 10. Hypothesis and Control of Cognitive Self-Motivation 9310.1. Social groups 9310.2. Innate self-motivation 9510.3. Mass communication 9610.4. The Cost–Benefit ratio 9710.5. Social representation 9810.6. The relational environment 9910.7. Perception 10010.8. Identity 10010.9. Social environment 10110.10. Historical antecedence 10210.11. Ethics 102Chapter 11. A Model of Self-Motivation which Associates Language and Physiology 10511.1. A new model 10511.2. Architecture of a self-motivation subsystem 10611.3. Level of certainty 10811.4. Need for self-motivation 10811.5. Notion of motive 10911.6. Age and location 11311.7. Uniqueness 11311.8. Effect of spontaneity 11411.9. Effect of dependence 11411.10. Effect of emulation 11511.11. Transition of belief 11511.12. Effect of individualism 11711.13. Modeling of the groups of beliefs 117Chapter 12. Impact of Self-Motivation on Written Information 12312.1. Platform for production and consultation of texts 12312.2. Informational measure of the motives of self-motivation 12412.2.1. Intra-phrastic extraction 12512.2.2. Inter-phrastic extraction 12612.2.3. Meta-phrastic extraction 12812.3. The information market 12912.4. Types of data 13012.5. The outlines of text mining 13312.6. Software economy 13912.7. Standards and metadata 13912.8. Open-ended questions and challenges for text-mining methods 14012.9. Notion of lexical noise 14112.10. Web mining 14312.11. Mining approach 145Chapter 13. Non-Transversal Text Mining Techniques 14713.1. Constructivist activity 14713.2. Typicality associated with the data 14813.3. Specific character of text mining 14813.4. Supervised, unsupervised and semi-supervised techniques 14913.5. Quality of a model 14913.6. The scenario 14913.7. Representation of a datum 15013.8. Standardization 15113.9. Morphological preprocessing 15213.10. Selection and weighting of terminological units 15313.11. Statistical properties of textual units: lexical laws 15413.12. Sub-lexical units 15513.14. Shallow parsing or superficial syntactic analysis 15713.15. Argumentation models 158Chapter 14. Transversal Text Mining Techniques 15914.1. Mixed and interdisciplinary text mining techniques 15914.1.1. Supervised, unsupervised and semi-supervised techniques 15914.2. Techniques for extraction of named entities 16014.3. Inverse methods 16314.4. Latent Semantic Analysis 16414.5. Iterative construction of sub-corpora 16514.6. Ordering approaches or ranking method 16514.7. Use of ontology 16614.8. Interdisciplinary techniques 16714.9. Information visualization techniques 16714.10. The k-means technique 16814.11. Naive Bayes classifier technique 16914.12. The k-nearest neighbors (KNN) technique 17014.13. Hierarchical clustering technique 17114.14. Density-based clustering techniques 17214.15. Conditional fields 17514.16. Nonlinear regression and artificial neural networks 17614.17. Models of multi-agent systems (MASs) 17714.18. Co-clustering models 17814.19. Dependency models 17914.20. Decision tree technique 17914.21. The Support Vector Machine (SVM) technique 18014.22. Set of frequent items 18214.23. Genetic algorithms 18414.24. Link analysis with a theoretical graph model 18414.25. Link analysis without a graph model 18514.26. Quality of a model 18614.27. Model selection 189Chapter 15. Fields of Interest for Text Mining 19115.1. The avenues in text mining 19115.1.1. Organization 19115.1.2. Discovery 19315.2. About decision support 19415.3. Competitive intelligence (vigilance) 19515.4. About strategy 19715.5. About archive management 20015.6. About sociology and the legal field 20315.7. About biology 21515.8. About other domains 219Conclusion 221Bibliography 225Index 267