The Second IEEE Workshop on
| ||||||
| About | Keynotes | Dates and Submission | Program | Student Travel Support | Organization | HMData 2017 |
About IEEE HMData 2018Overview
Human power is a key factor to maximize the impact of bigdata technologies. This workshop addresses human-in-the-loop approaches in bigdata lifecycle - in collecting, processing, analyzing, utilizing, archiving and disposing them. The purpose of this workshop is to give excellent opportunities for students, researchers and practitioners to identify important research problems and exchange their ideas on human-in-the-loop in the bigdata context. To make the workshop an attractive place for those people, we solicit practitioner papers as well as research papers, in order to facilitate discussion among researchers who know solutions and practitioners who know problems.
We also would like to make the place valuable for young researchers.
All papers accepted for the workshop will be included in the Workshop Proceedings published by the IEEE Computer Society Press, made available at the Conference.
Topics
This workshop covers a wide range of human-related topics in the bigdata context, such as crowdsourcing, collaborative recommendation, crowdsensing, workflow model for humans and machines, incentives, human-assisted bigdata analysis, bigdata-human interaction, supporting tools for humans in human-in-the-loop systems, security and privacy in human-machine collaboration , human factors and ELSI (ethical, legal and social issues) in human-in-the-loop systems, and human-machine collaboration in real-world problems.
Keynotes
Decision Theoretical Crowdsourcing
Dan Weld (University of Washington) 
Abstract: Requestors often complain about the low-quality of crowd work,
but what is the underlying cause? We argue that traditional quality-control techniques
like majority vote and expectation maximization (EM) miss the point and don’t solve the true,
underlying problems: confusing task instructions, poor worker training, and poor allocation
of tasks to workers. Instead we advocate three new methods based on decision theory:
1) gated instruction, 2) adaptive testing, 3) micro-argumentation, and 4) self-improving workflows.
These methods fuse ideas from HCI with AI methods such as partially-observable Markov decision problems &
reinforcement learning. As a bonus, we’ll present recent work on active learning, where the crowd does
more than just label examples.
Bio:
Daniel S. Weld is Thomas J. Cable / WRF Professor in the Paul G. Allen School of Computer Science & Engineering and Entrepreneurial Faculty Fellow at the University of Washington. After formative education at Phillips Academy, he received bachelor's degrees in both Computer Science and Biochemistry at Yale University in 1982. He landed a Ph.D. from the MIT Artificial Intelligence Lab in 1988, received a Presidential Young Investigator's award in 1989, an Office of Naval Research Young Investigator's award in 1990, was named AAAI Fellow in 1999 and deemed ACM Fellow in 2005. Dan was a founding editor for the Journal of AI Research, was area editor for the Journal of the ACM, guest editor for Computational Intelligence and Artificial Intelligence, and was Program Chair for AAAI-96. Dan has published two books and scads of technical papers.
Dan is an active entrepreneur with several patents and technology licenses. He co-founded Netbot Incorporated, creator of Jango Shopping Search (acquired by Excite), AdRelevance, a monitoring service for internet advertising (acquired by Nielsen NetRatings), and data integration company Nimble Technology (acquired by Actuate). Dan is a Venture Partner at the Madrona Venture Group and on the Scientific Advisory Boards of the Allen Institute for Artificial Intelligence and the Madrona Venture Group.
Dan teaches many courses, including graduate classes on Artificial Intelligence, Extracting, Managing & Personalizing Web Information and Intelligent User Interfaces, and undergraduate classes on Artficial Intelligence, Advanced Internet Systems, and Machine Learning. In 2012, Dan co-organized a workshop on Crowdsourcing Personalized Online Education. During sabbaticals Dan was a visiting professor at Griffith University in Brisbane, Australia and visited the VIBE group at Microsoft Research.
ProgramLabels: [FR] - Full Paper (Research-oriented), [FP] - Full Paper (Practice-oriented), [R] Project-in-Progress Paper (Research-oriented), [P] Project-in-Progress Paper (Practice-oriented)Participant Survey QuestionsWe would like to sincerely ask every participant to answer participant survey questions. It takes only one minute to answer. The aggregated values will be open to the participants of the workshop venue to share who we are and what are topics they are interested in8:45 Opening (WS Chairs)8:50-10:10 Session 1 (Chair: TBA)8:50 [FR] Maria Stefan, Jose Gutierrez Lopez, and Rasmus Løvenstein Olsen. Exploring the Potential of Modern Advanced Metering Infrastructure in Low-Voltage Grid Monitoring Systems9:20 [R] Hidehiko Shishido, Emi Kawasaki, Yutaka Ito, Youhei Kawamura, Toshiya Matsui, and Itaru Kitahara. Time-Lapse Image Generation using Image-Based Modeling by Crowdsourcing 9:30 [R] Yusuke Suzuki, Masaki Matsubara, Keishi Tajima, Toshiyuki Amagasa, and Atsuyuki Morishima. A Cache-based Approach to Dynamic Switching between Different Dataflows in Crowdsourcing 9:40 [P] Flavia Fulco, Munenari Inoguchi, and Tomoya Mikami. Cyber-Physical Disaster Drill: Preliminary Results and Social Challenges of the First Attempts to Unify Human, ICT and AI in Disaster Response 9:50 [R] Tomoya Mikami, Masaki Matsubara, Takashi Harada, and Atsuyuki Morishima. Worker Classification based on Answer Pattern for Finding Typical Mistake Patterns 10:00 [R] Takafumi Suzuki, Satoshi Oyama, and Masahito Kurihara. Toward Explainable Recommendations: Generating Review Text from Multicriteria Evaluation Data 10:10-10:30 Coffee Break10:30-12:00 Session 2 (Chair: Satoshi Oyama)10:30 [FP] Keiko Tamura, Munenari Inoguchi, Kei Horie, Ryota Hamamoto, and Haruo Hayashi. Realization of Effective Team Management Collaborating between Cloud-based System and On-site Human Activities -A Case Study of Building Damage Inspection at 2018 Hokkaido Eastern Iburi Earthquake-11:00 [FR] Masaki Matsubara, Masaki Kobayashi, and Atsuyuki Morishima. A Learning Effect by Presenting Machine Prediction as a Reference Answer in Self-correction 11:30 [R] Huang Li, Shiaofen Fang, Snehasis Mukhopadhyay, Andrew Sakin, and Li Shen. Interactive Machine Learning by Visualization: A Small Data Solution 11:40 [R] Nadeesha Wijerathna, Masaki Matsubara, and Atsuyuki Morishima. Finding Evidences by Crowdsourcing 11:50 [R] Koyo Kobayashi, Hidehiko Shishido, Yoshinari Kameda, and Itaru Kitahara. A Method to Collect Multi-view Images of High Importance Using Disaster Map and Crowdsourcing 12:00-13:30 Lunch13:30-15:00 Session 3 (Chair: Senjuti Basu Roy) 13:30 Keynote by Dan Weld (University of Washington)
14:30 [FR] Yoko Yamakata, Keishi Tajima, and Shinsuke Mori. A Case Study on Start-up of Dataset Construction: In Case of Recipe Named Entity Corpus | ||||||
