Hybrid Crowdsensing

Abstract

Crowdsensing systems can be either participatory or opportunistic, depending on whether the user intentionally contributes data, or she simply acts as the bearer of a sensing device from which data is transparently collected. In this paper, we propose hybrid crowdsensing, a social mediabased paradigm which aims at combining the strengths of both participatory and opportunistic crowdsensing. With hybrid crowdsensing, possibly relevant data is collected via an opportunistic approach. Then, users that spontaneously contributed are directly contacted and asked to provide additional information following a participatory approach. To demonstrate its feasibility and usefulness, we experimented the proposed paradigm for involving Twitter users in an emergency relief scenario. For each of the two real-world experiments we analyze the answer ratio to our questions, their time distribution, and responders' willingness to collaborate. Results support the adoption of hybrid crowdsensing, especially in those practical scenarios where users are emotionally involved.

Measuring objective and subjective well-being: dimensions and data sources

“…Results mostly show consistency between all data sources. In conjunction with social media and crowdsourcing data sources, as well as environmental and safety dimensions, Avvenuti et al [256] collect targeted and detailed information from people involved in natural disasters through crowdsourcing surveys via social media. These data are used to monitor unfolding disasters better and to monitor their consequences (i.e., damage caused)…”

Multimodal detection of epilepsy with deep neural networks

“…In the present study, we exploit the set of genuine accounts and the set of social spambots #1. For collecting genuine users, the authors adopted the methodology proposed in [38]. Specifically, the authors contacted with some accounts and asked them a question.…”

Social Welfare-Based Task Assignment in Mobile Crowdsensing

“…The study designed a participatory worker recruitment algorithm based on sensing subregion clustering in the present phase. Avvenuti et al (2017) designed a hybrid sensing approach that operated based on social media, which could collect perceptual data through an opportunistic approach by contacting spontaneous contributing users, then asking them to provide more data according to a participatory approach. These methods, however, do not consider the impact of task pricing on workers, which affects social welfare.…”

“…Participatory/ Opportunistic Sensing Social Welfare He et al, 2014;Tao & Song, 2018;Wang et al, 2016;J. Wang et al, 2018 Pu et al, 2017;Xiong et al, 2014;Xiong et al, 2015aXiong et al, , 2015b × ×/✓ × Guo et al, 2016;Wei et al, 2023;Wang et al, 2020;Lu & Zhu, 2020;Avvenuti et al, 2017…”