Theoretical and Logical Methods -- On Special Functions and Theorem Proving in Logics for ‘Generally’ -- First-Order Contextual Reasoning -- Logics for Approximate Reasoning: Approximating Classical Logic “From Above” -- Attacking the Complexity of Prioritized Inference Preliminary Report -- A New Approach to the Identification Problem -- Towards Default Reasoning through MAX-SAT -- Autonomous Agents and Multi-agent Systems -- Multiple Society Organisations and Social Opacity: When Agents Play the Role of Observers -- Altruistic Agents in Dynamic Games -- Towards a Methodology for Experiments with Autonomous Agents -- How Planning Becomes Improvisation? — A Constraint Based Approach for Director Agents in Improvisational Systems -- Extending the Computational Study of Social Norms with a Systematic Model of Emotions -- A Model for the Structural, Functional, and Deontic Specification of Organizations in Multiagent Systems -- The Queen Robots: Behaviour-Based Situated Robots Solving the N-Queens Puzzle -- The Conception of Agents as Part of a Social Model of Distance Learning -- Emotional Valence-Based Mechanisms and Agent Personality -- Simplifying Mobile Agent Development through Reactive Mobility by Failure -- Dynamic Social Knowledge: The Timing Evidence -- Machine Learning -- Empirical Studies of Neighborhood Shapes in the Massively Parallel Diffusion Model -- Ant-ViBRA: A Swarm Intelligence Approach to Learn Task Coordination -- Automatic Text Summarization Using a Machine Learning Approach -- Towards a Theory Revision Approach for the Vertical Fragmentation of Object Oriented Databases -- Speeding up Recommender Systems with Meta-prototypes -- ActiveCP: A Method for Speeding up User Preferences Acquisition in Collaborative Filtering Systems -- Making Recommendations for Groups Using Collaborative Filtering and Fuzzy Majority -- Knowledge Discovery and Data Mining -- Mining Comprehensible Rules from Data with an Ant Colony Algorithm -- Learning in Fuzzy Boolean Networks — Rule Distinguishing Power -- Attribute Selection with a Multi-objective Genetic Algorithm -- Applying the Process of Knowledge Discovery in Databases to Identify Analysis Patterns for Reuse in Geographic Database Design -- Lithology Recognition by Neural Network Ensembles -- Evolutionary Computation and Artificial Life -- 2-Opt Population Training for Minimization of Open Stack Problem -- Grammar-Guided Genetic Programming and Automatically Defined Functions -- An Evolutionary Behavior Tool for Reactive Multi-agent Systems -- Controlling the Population Size in Genetic Programming -- Uncertainty -- The Correspondence Problem under an Uncertainty Reasoning Approach -- Random Generation of Bayesian Networks -- Evidence Propagation in Credal Networks: An Exact Algorithm Based on Separately Specified Sets of Probability -- Restoring Consistency in Systems of Fuzzy Gradual Rules Using Similarity Relations -- Natural Language Processing -- Syntactic Analysis for Ellipsis Handling in Coordinated Clauses -- Assessment of Selection Restrictions Acquisition.

The biennial Brazilian Symposium on Arti?cial Intelligence (SBIA 2002) – of which this is the 16th event – is a meeting and discussion forum for arti?cial intelligence researchers and practitioners worldwide. SBIA is the leading c- ference in Brazil for the presentation of research and applications in arti?cial intelligence. The ?rst SBIA was held in 1984, and since 1995 it has been an international conference, with papers written in English and an international program committee, which this year was composed of 45 researchers from 13 countries. SBIA 2002 was held in conjunction with the VII Brazilian Symposium on Neural Networks (SBRN 2002). SBRN 2002 focuses on neural networks and on other models of computational intelligence. SBIA 2002, supported by the Brazilian Computer Society (SBC), was held in Porto de Galinhas/Recife, Brazil, 11–14 November 2002. The call for papers was very successful, resulting in 146 papers submitted from 18 countries. A total of 39 papers were accepted for publication in the proceedings. We would like to thank the SBIA 2002 sponsoring organizations, CNPq, Capes, and CESAR, and also all the authors who submitted papers. In particular, we would like to thank the program committee members and the additional referees for the di?cult task of reviewing and commenting on the submitted papers.