Towards human centric querying and decision making: dealing with pros-and-cons type bipolarity in intentions, judgments and evaluations
By Janusz Kacprzyk
We are concerned with some big challenges facing IT/ICT for a long time which can be briefly stated as those related to making computers to be "cognitive partners" for the humans. We concentrate on a purposeful use of vast data and information resources. We are concerned, first, on how to find (retrieve) a proper information reflecting the human needs, interests, intentions, preferences, etc. Then, we deal with how to purposefully use that information for decision making which is a ``meta-problem'' in all human activities. Since decisions are made by humans, and for the humans, even if mimicked by/in inanimate systems, then the decision making is a clear human centric/centered problem, and so is querying. Formally, decision making boils down to finding a best option, usually using some strict and formal choice or optimization tools. In real situations, we should add some elements to our models to make them more human consistent, hence easier implementable, notably some adequate representations of human judgments, attitudes, preferences and intentions, for instance which involve an element of a positive and negative, necessary and optional, etc. evaluations, or the pros and cons, for short. We are concerned with how to formalize and solve problems in which there is a bipolarity in the decision maker’s judgments, intentions and preferences which boils down in our context to the specification of what is necessary and optional, and therefore what should result in the rejection and acceptance of an option or course of action. We present the concept of a bipolar query exemplified by, for a real estate example: find a house which is more or less within our price limit and, if possibly, close to public transportation, or – when context is involved – find such a house among houses that are possibly characteristic for a specific zone. The problem is clearly a non-standard “and, if possibly” aggregation which can be modeled by fuzzy logic. We also show how, using a similar approach, a bipolar decision making setting can be devised, from various points of view, notably non-orthodox multicriteria and multiagent, and dynamic decision making, using fairness analyses, intention modeling, multiagent approaches, etc. We indicate potentials of this bipolar type approaches to solve human centric problems which are particularly relevant for modern IT/ICT based environments.
Academician Janusz Kacprzyk, Fellow of IEEE, IET, IFSA, EurAI and SMIA, graduated from Warsaw University of Technology, Poland, with M.Sc. in automatic control and computer science, obtained in 1977 Ph.D. in systems analysis and in 1991 D.Sc. in computer science. He is Professor of Computer Science at the Systems Research Institute, Polish Academy of Sciences, WIT – Warsaw School of Information Technology, Chongqing Three Gorges University, Wanzhou, China, and Professor of Automatic Control at PIAP – Industrial Institute of Automation and Measurements. He is Honorary Foreign Professor at the Department of Mathematics, Yli Normal University, Xinjiang, China. He is Full Member of the Polish Academy of Sciences, Member of Academia Eureopaea (Informatics), Member of European Academy of Sciences and Arts (Technical Sciences), Foreign Member of the Bulgarian Academy of Sciences, Spanish Royal Academy of Economic and Financial Sciences (RACEF), Finnish Society of Sciences and Letters, Flemish Royal Academy of Belgium for Sciences and the Arts (KVAB) and the International Academy of Systems and Cybernetics.. He received the honorary doctorates (doctor honoris causa) from Széchenyi István University, Győr, Hungary, 2014; Óbuda University, Budapest, Hungary, 2016; Professor Zlatarev University, Bourgas, Bulgaria, 2017; and Lappeenranta University of Technology, Lappeenranta, Finland, 2017. He has been a frequent visiting professor in the USA, Italy, UK, Mexico, China, Austria, and Bulgaria and served on evaluation commissions of many foreign universities, as well as on panels for Advanced Grants at the European Research Council. His main research interests include the use of modern computation computational and artificial intelligence tools, notably fuzzy logic, in decisions, optimization, control, data analysis and data mining, with applications in databases, ICT, mobile robotics, systems modeling etc. He authored 6 books, (co)edited more than 100 volumes, (co)authored ca. 550 papers. He is a member of the IEEE CIS Award Committee, was Chair of 2016 IEEE CIS Award Committee, was in 2011 – 2016, and is from 2018 a member of Adcom of IEEE CIS, and was a Distinguished Lecturer of IEEE CIS. He received many awards notably the 2006 IEEE CIS Pioneer Award in Fuzzy Systems, 2006 Sixth Kaufmann Prize and Gold Medal for pioneering works on soft computing in economics and management, 2007 Pioneer Award of the Silicon Valley Section of IEEE CIS for contribution in granular computing and computing in word. He is the President of the Polish Operational and Systems Research Society and Past President of International Fuzzy Systems Association.
Understanding Human Behavior in Online Social Networks
By Athena Vakali
Online social networks interactions generate massive data threads at unprecedented rates. Several sectors (commercial, advertising, politics, learning, and many more) are highly impacted by online social behavioral norms which challenge todays trust, growth, and decision making. Harvesting knowledge from such data is crucial since human sentiment, personality traits, and emerging phenomena can be captured under different contexts. In this talk, focus is placed on understanding the entities, the processes, and the patterns by which humans generate, disseminate, and consume information in online social networks. Online personality formulation and behavioral patterns detection will be outlined, based on users features and profiling. Emphasis will be given on the methods which have been extensively used in the field of sentiment analysis. Opinion mining and affective analysis will be comparatively discussed with reference to relevant data mining, machine learning, and hybrid approaches. Indicative methods for online users behavioral dynamics and struggling phenomena (fakeness, cyberaggression, etc) will also be presented highlighting the limitations and current challenges in online social networks information exchange processes. Conclusions and future work insights will be summarized and discussed.
Athena Vakali is a Professor and Vice Chair at the School of Informatics, Aristotle University, Greece, where she leads the research Laboratory on Data and Web science (Datalab). She holds a PhD degree in Informatics (Aristotle University), a MSc degree in Computer Science (Purdue University, USA) and a BSc in Mathematics (Aristotle University). Her current research interests include big data mining and analytics, AI algorithms for Next Generation Internet, smart cities data analytics, online social networks mining, as well as on online sources data management on the cloud. Her publication record of over 160 papers received over 7100 citations (h-index 35 in Google scholar). She has served as a member in the EU Steering Committee for the Future Internet Assembly (2012-14) and she has participated in more than 30 research projects (EU FP7, H2020, International and national funds). She has co-chaired major Conferences Committees such as IEEE/ACM/WIC Web Intelligence 2019, EAI 2016 Conference on Future Internet Infrastructures, Enablers and EU Internet Science Conference 2015, ACM International Conference on Web Information Systems Engineering, etc. More details about her research can be found at https://datalab.csd.auth.gr/