A comprehensive reputation assessment framework for volunteered geographic information in crowdsensing applications
- 221 Downloads
Volunteered geographic information (VGI) is the result of activities where individuals, supported by enabling technologies, behave like physical sensors by harvesting and organizing georeferenced content, usually in their surroundings. Both researchers and organizations have recognized the value of VGI content, however this content is typically heterogeneous in quality and spatial coverage. As a consequence, in order for applications to benefit from it, its quality and reliability need to be assessed in advance. This may not be easy since, typically, it is unknown how the process of collecting and organizing the VGI content has been conducted and by whom. In the literature, various proposals focus on an indirect process of quality assessment based on reputation scores. Following this perspective, the present paper provides as main contributions: (i) a multi-layer architecture for VGI which supports a process of reputation evaluation; (ii) a new comprehensive model for computing reputation scores for both VGI data and contributors, based on direct and indirect evaluations expressed by users, and including the concept of data aging; (iii) a variety of experiments evaluating the accuracy of the model. Finally, the relevance of adopting this framework is discussed via an applicative scenario for recommending tourist itineraries.
KeywordsSocial sensors Reputation evaluation Feedback-based model Indirect feedback Volunteered geographic information Mobile crowdsourcing Tourism planning
The Authors are thanking the colleague Prof. Gianfranco Lamperti for his very valuable help in supporting the work described in this paper, and the former student Eng. Marco Gusmini for developing the first prototypes of the proposed solution.
- 1.Aroyo L, Welty C (2013) Crowd truth: harnessing disagreement in crowdsourcing a relation extraction gold standard. WebSci2013 ACM 2013Google Scholar
- 2.Bishr M, Kuhn W (2013) Trust and reputation models for quality assessment of human sensor observations. In: Tenbrink T, Stell J, Galton A, Wood Z (eds) Spatial information theory: 11th international conference, COSIT 2013, Scarborough, UK, Proceedings. Springer International Publishing, Cham, pp 53–73. https://doi.org/10.1007/978-3-319-01790-7_4 CrossRefGoogle Scholar
- 7.D’Antonio F, Fogliaroni P, Kauppinen T (2014) VGI edit history reveals data trustworthiness and user reputation. In: 17th AGILE international conference on geographic information Science (Short Paper)Google Scholar
- 12.Jokar AJ, Mooney P, Zipf A, Schauss A (2015) Quality assessment of the contributed land use information from openstreetmap versus authoritative datasets. In: OpenStreetMap in GIScience. Springer, pp 37–58Google Scholar
- 14.Keßler C, Trame J, Kauppinen T (2011) Tracking editing processes in volunteered geographic information: the case of openstreetmap. Identifying objects, processes and events in spatio-temporally distributed data (IOPE), workshop at conference on spatial information theory, p 12Google Scholar
- 20.Veregin H (1999) Data quality parameters. Geogr Inf Syst 1:177–189Google Scholar
- 21.Xiao C, Freeman DM, Hwa T (2015) Detecting clusters of fake accounts in online social networks. In: Proceedings of the 8th ACM workshop on artificial intelligence and security, ACM, New York, AISec ’15, pp 91–101. https://doi.org/10.1145/2808769.2808779
- 23.Ye B, Wang Y (2016) Crowdrec: Trust-aware worker recommendation in crowdsourcing environments. In: 2016 IEEE international conference on web services (ICWS), pp 1–8. https://doi.org/10.1109/ICWS.2016.10
- 24.Yu B, Singh MP (2002) An evidential model of distributed reputation management. In: Proceedings of the first international joint conference on autonomous agents and multiagent systems: Part 1. ACM, pp 294–301Google Scholar
- 25.Yu H, Shen Z, Leung C (2013) Bringing reputation-awareness into crowdsourcing. In: 2013 9th international conference on information, communications signal processing, pp 1–5. https://doi.org/10.1109/ICICS.2013.6782912