Invited Speakers

Prof. Hiroshi Motoda, Osaka University, Japan

Title: Which is More Influential, “Who” or “When” for a User to Rate in Online Review Site?

Abstract: I start with often discussed difficult problems in social network analysis and how we challenge these problems without technical details. These include computation of influence degree in information diffusion in social network, learning diffusion probability, identifying influential people, super mediators and critical links, and detecting changes. Then, I focus on one of the problems which is identifying influential users in online review systems.

At its heart the act of reviewing is very subjective, but in reality many factors influence user's decision. This can be called social influence bias. We pick two factors, “Who” and “When” and discuss which factor is more influential when a user posts his/her own rate after reading the past review scores in an online review system. We show that a simple model can learn the factor metric quite efficiently from a vast amount of data that is available in many online review systems and clarify that there is no universal solution and the influential factor depends on each dataset. We use a weighted multinomial generative model that takes account of each user's influence over other users. We consider two kinds of users: real and virtual, in accordance with the two factors, and assign an influence metric to each. In the former each user has its own metric, but in the latter the metric is assigned to the order of review posting actions (rating). Both metrics are learnable quite efficiently with a few tens of iterations by log-likelihood maximization. Goodness of metric is evaluated by the generalization capability. The proposed method was evaluated and confirmed effective by five review datasets. Different datasets give different results. Some dataset clearly indicates that user influence is more dominant than the order influence while the results are the other way around for some other dataset, and yet other dataset indicates that both factors are not relevant. The third one indicates that the decision is very subjective, i.e., independent of others' review. We tried to characterize the datasets, but were only partially successful. For datasets where user influence is dominant, we often observe that high metric users have strong positive correlations with three more basic metrics: 1) the number of reviews a user made, 2) the number of the user's followers who rate the same item, 3) the fraction of the user's followers who gave the similar rate, but this is not always true. We also observe that the majority of users is normal (average) and there are two small groups of users, each with high metric value and low metric value. Early adopters are not necessarily influential.

Biography: Hiroshi Motoda is Professor Emeritus of Osaka University, Guest Professor of the Institute of Scientific and Industrial Research (ISIR) of Osaka University. He was a scientific advisor at AFOSR/AOARD (Asian Office of Aerospace Research and Development, Air Force Office of Scientific Research, US Air Force Research Laboratory) since 2006 till 2018, and worked as an international program officer. Before that, he was a professor in the division of Intelligent Systems Science at the Institute of Scientific and Industrial Research of Osaka University since 1996 until March, 2006. Before joining the university, he had been with Hitachi since 1967. At Hitachi he participated in research on nuclear reactor core management, diagnosis, control and design until 1985, and then moved to the field of machine learning, knowledge acquisition, qualitative reasoning and diagrammatic reasoning. After joining the university, he extended his research to scientific knowledge discovery and data mining. At AOARD he worked on social network analysis while managing several basic research projects on Computational Intelligence. He received his BSc, MSc and PhD degrees, all in nuclear engineering from the University of Tokyo. He is now an honorary member of the steering committee of Asian Conference on Machine Learning (ACML), an honorary member of the steering committee of Pacific Rim International Conference of Artificial Intelligence (PRICAI), a life long member of the steering committee of Pacific Asian Conference of Knowledge Discovery and Data Mining (PAKDD), and a steering committee member of IEEE International Conference on Data Science and Advanced Analytics (DSAA). He received the best paper awards twice from Atomic Energy Society of Japan and three times from Japanese Society for Artificial Intelligence (JSAI), the outstanding achievement awards from JSAI, the distinguished contribution award from PAKDD and PRICAI, and the outstanding contribution award from Web Intelligence Consortium. He wrote/edited four books on feature selection/extraction/construction. His book “Fundamentals of Data Mining” was awarded the 2007 Okawa Publishing Prize. He is a fellow of JSAI.

Prof. Alex Singleton, University of Liverpool, UK

Title: Illuminating the Structure and Function of Cities through Consumer Data

Abstract: Many data sources that social scientists have traditionally relied upon for their scholarly work to understand the structure and function of cities are increasingly under threat, which may challenge future progress if we are slow to adapt to this evolving data economy. Such threats include a trend of declining response rates in many large scale social surveys leading to increased uncertainty, growing scrutiny of the rising costs of conducting a national Census, and numerous cases of either access to open data being removed or their use stifled through more restrictive licenses. In parallel, many new forms of transactional data are emerging that are challenging traditional models of inquiry, both from the perspective of infrastructure that enable their management, aligned with skills shortages in those methods that enable insight to be extracted. This talk will highlight progress made within the UK through the establishment of the ESRC funded Consumer Data Research Centre and a number of applications of "Big" consumer data to applications providing new insight about the structure and function of cities.

Biography: Alex Singleton is Professor of Geographic Information Science at the University of Liverpool, where he entered as a lecturer in 2010. He holds a First Class BSc (Hons) Geography from the University of Manchester and a PhD from University College London. To date, his research income totals around £15m, with two career highlights including the ESRC funded Consumer Data Research Centre; and the recently awarded ESRC Centre for Doctoral Training in New Forms of Data. Alex’s research is embedded within the Geographic Data Science Lab (geographicdatascience.com) and concerns various aspects of urban analytics. In particular, his work has extended a tradition of area classification within Geography where he has developed an empirically informed critique of the ways in which geodemographic methods can be refined for effective yet ethical use in public resource allocation applications.

Prof. James Ferryman, University of Reading, UK

Title: Smart Cities: How Advanced Data Analytics, Biometrics and Related Technologies will Revolutionise Border Crossing

Abstract: Traveller numbers worldwide are without doubt increasing and this includes travellers to Da Nang reflecting the city's outward-looking culture and its interest in promoting its tourism to the rest of the world. The number of international travellers to Da Nang increased by 36.8% from 2016 to 2.3 million in 2017. This includes the number of air visitors increasing to 1.58 million, an increase of 74%. However, threats to stability and citizen welfare include terrorism, organised crime and smuggling. Hence there is a need for a smart city such as Da Nang to facilitate expedited border crossings for travellers but at the same time ensure the security, effectiveness and the integrity of the immigration control. This talk will present the current situation in Europe regarding the development and deployment of of Automated Border Control (ABC). Specifically, ABC eGates at airports have enabled biometric verification to be performed using passports more rapidly and accurately than traditional manual checking. The talk will present the outcomes of a recently completed 4-year EU project called FastPass which aimed to develop a harmonised approach to Automated Border Control (ABC) eGates incorporating both innovative development and application of biometrics and video surveillance. However, it may be argued that such innovations still do not meet expectations. Specifically, an unexpected side effect of greater automation is that queues for eGates can sometimes exceed the length of queues for the manual controls. This is because the transaction times for eGates are still unacceptably long. The talk will therefore propose a vision of the future of ABC for the next 5-10+ years whereby eGates are replaced with a biometrics on-the-move no-gate system taking into account privacy and security issues. In this context, the current EC PROTECT project will be presented including the innovative scenarios that are being developed and an overview of the proposed technical solutions. Furthermore, an integral part of no-gate solutions is the concept of advance traveller risk analysis, whereby border authorities are able to identify persons of interest before their arrival at the border crossing point, based on database checks and intelligence. Therefore, to cope with the increase in information coming from information systems, border control officers will also need new data analytic tools to support immigration decisions.

Biography: Professor James Ferryman, Professor of Computational Vision, Computer Science (SMPCS), University of Reading Prof. Ferryman (M'96) received the B.S. degree in computer science in 1990 and the Ph.D. degree in computational vision in 2000, both from the University of Reading, Reading, U.K. In 2014 he became full professor. Prof. Ferryman is a data scientist and leads the Computational Vision Group within the Department of Computer Science, School of Mathematical, Physical and Computational Sciences (SMPCS), and has previously acted as Director of Research for the School of Systems Engineering, University of Reading. His current research interests include automated video surveillance, multimodal biometrics and performance evaluation. He is the author of more than 100 scientific publications. He has participated in a wide range of UK and EU funded research programmes including the EU EFFISEC project (FP7-217991) on efficient integrated security checkpoints and the EU FastPass project (FP7-312583) on development of a harmonised modular reference system for all European automated crossing points. Prof. Ferryman currently coordinates the 10 partner EU PROTECT project (H2020-700259, 2016-2019) on exploration of current and future use of biometrics in border control. Prof. Ferryman is a member of the British Computer Society and has acted as the Director of both the British Machine Vision Association and the Security Information Technology Consortium. Since 2000, he has been a Co-Chair of the IEEE International Workshop on Performance Evaluation of Tracking and Surveillance.

Prof. Ho Tu Bao, Vietnam Institute for Advanced Study in Mathematics (VIASM) and John von Neumann Institute (JVN), Vietnam

Title: Some issues of cities in Vietnam in the digital transformation time

Abstract: We share our opinions on some issues relating to data science in development of cities in Vietnam in the digital transformation time. First is building digital infrastructure in which we emphasize on building the data infrastructure. Second is healthcare data in particular the implementation and exploitation of electronic medical records. Third is the analysis of traffic data in reducing transformation accidents and improving some logistics tasks.

Biography: Ho Tu Bao is Professor Emeritus of Japan Advanced Institute of Science and Technology (JAIST), Director of the John von Neumann Institute (JVN) of Vietnam National University at Ho Chi Minh City and Director of Data Science Lab of the Vietnam Institute for Advanced Study in Mathematics (VIASM). He graduated (1978) from Hanoi University of Technology, Master (1984) and Doctor (1987) in Artificial Intelligence from the Universite Paris 6, and Habilitation a diriger de recherche (1998) from the University Paris 9. He has been doing research, application and teaching in the fields of Artificial Intelligence, Machine Learning, Data Mining, and more recently in Data Science for more than thirty years. He is members of the Steering Committee of PRICAI (Pacific Rim International Conference on Artificial Intelligence), PAKDD (Pacific Asia Knowledge Discovery and Data Mining), ACML (Asia Conference on Machine Learning)