Task Assignment Optimization
How can we optimally match people to tasks?
To ensure quality, cost efficiency and timeliness in the production of expert tasks (as in knowledge-intensive crowdsourcing or innovation organisations) while accounting for the needs, motivation and talents of the expert workers, I develop task-to-user matching mechanisms that combine resource scheduling, traditionally found in operational research, with non-deterministic behavioral modelling.
To ensure quality, cost efficiency and timeliness in the production of expert tasks (as in knowledge-intensive crowdsourcing or innovation organisations) while accounting for the needs, motivation and talents of the expert workers, I develop task-to-user matching mechanisms that combine resource scheduling, traditionally found in operational research, with non-deterministic behavioral modelling.
|
|
Task assignment optimization in knowledge-intensive crowdsourcing
VLDB journal Get PDF View in Springer It's about time: Online Macrotask Sequencing in Expert Crowdsourcing arXiv:1601.04038 Get PDF View in arXiv |
|
Tacit knowledge harnessing in corporate environments through collective intelligence, machine learning and resource allocation techniques
Xerox Europe - Invited talk |
Virtual Teams
How to form successful teams across time and space boundaries?
Remote collaboration can be hampered by ineffective communication and interpersonal conflicts. To address this, I work on algorithms that harness key behavioral and social characteristics of the candidate teammates (like personality or group dynamics) and use them to bring together more harmonious and performant virtual teams.
Remote collaboration can be hampered by ineffective communication and interpersonal conflicts. To address this, I work on algorithms that harness key behavioral and social characteristics of the candidate teammates (like personality or group dynamics) and use them to bring together more harmonious and performant virtual teams.
|
|
|
|
Personality Matters: Balancing for Personality Types Leads to Better Outcomes for Crowd Teams
CSCW 2016 Get PDF View in ACM |
Open Innovation
What are the principles underlying radical innovation by many?
Expert identification & Performance prediction
Which user knows what in online communities? How can we predict future user performance?
I use machine learning to analyse the past performance of people in online communities (wikis, e-learning) and predict their future knowledge contribution quality and overall performance.
I use machine learning to analyse the past performance of people in online communities (wikis, e-learning) and predict their future knowledge contribution quality and overall performance.
|
CorpWiki: A self-regulating wiki to promote corporate collective intelligence through expert peer matching
Information Sciences Get PDF View in Elsevier |
Dropout prediction in e-learning courses through the combination of machine learning techniques
Computers & Education Get PDF View in Elsevier |
Online knowledge communities
What makes a wiki knowledge community successful? How can organisations successfully integrate wikis into their day-to-day processes?
|
|
Planning for a successful corporate wiki
DEIS'11 Get PDF View in Springer Wikis in enterprise settings: A survey Enterprise Information Systems Get PDF View in Taylor & Francis |
Cyber-physical Crowds
Urban Discovery in Smart Cities
How can technology help citizens reflect on and re-interpret their urban environment?
|
|
Co-Designing a Location-based Digital Game by Paper Prototyping using a Board Game
ACM CHI 2017 - Case Studies Get PDF View in ACM |
Path routing personalization
Which Points of Interest should we recommend to museum or city visitors to improve their Quality of Experience?
|
|
Improving museum visitors’ Quality of Experience through intelligent recommendations: A visiting style-based approach
IE' 13 - Workshops Get PDF View in IOS Press Related Software: Museum crowd simulator Created with the team at CRP Henri Tudor, Copyright: LIST View in Experimedia BLUE website |