Detection of Damage and Failure Events of Critical Public Infrastructure using Social Sensor Big Data

Tien, Iris; Musaev, Aibek; Benas, David; Ghadi, Ameya; Goodman, Seymour E.; Pu, Calton

doi:10.5220/0005932104350440

Cited by 22 publications

(9 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…(3) Tien et al recommend using social sensor to detect failure events or damages in main infrastructure systems, including bridges, highways, gas lines, and power infrastructures, in hope to compensate the lack of continuous physical monitoring sensors. They develop three-step filtering approach on text to filter out noises in social sensors [40].…”

Section: Discussionmentioning

confidence: 99%

Understanding Social Media Beyond Text: A Reliable Practice on Twitter

Hou

Han

2020

Preprint

View full text Add to dashboard Cite

Social media has been broadly applied in many applications in sales, marketing, event detection, etc. With high-volume and real-time data, social media has also been used for disaster responses. However, distinguishing between rumors and reliable information can be challenging, since social media, a user-generated content system, has a great number of users who update massive information every second. Furthermore, the rich information is not only included in the short text content but also embedded in the images, videos. In this paper, to address the emerging challenge of disaster response, we introduce a reliable framework for disaster information understanding and response with a practice on Twitter. The framework integrates both textual and imagery content from tweets in hope to fully utilize the information. The text classifier is built to remove noises, which can achieve 0.92 F1-score in classifying individual tweet. The image classifier is constructed by fine-tuning pre-trained VGG-F network, which can achieve 90\% accuracy. The image classifier serves as a verifier in the pipeline to reject or confirm the detected events. The evaluation indicates that the verifier can significantly reduce false positive events. We also explore Twitter-based drought management system and infrastructure monitoring system to further study the impacts of imagery content on event detection systems and we are able to pinpoint additional benefits which can be gained from social media imagery content.

show abstract

Section: Discussionmentioning

confidence: 99%

Understanding Social Media Beyond Text: A Reliable Practice on Twitter

Hou

Han

2020

Preprint

View full text Add to dashboard Cite

show abstract

“…During this process we consulted categories developed in prior content analyses of crisis-related social media [26,31]. While coding we noticed a diversity of information reporting forms of infrastructure damage prior studies suggest can support situational awareness during a crisis, including tweets reporting damage to buildings [26], roadways [12,33], and electrical infrastructure [4,17]. While this work informed our grounded analysis, the data we encountered revealed types of information that unpacked categories developed in prior research.…”

Section: Qualitative Content Analysismentioning

confidence: 92%

Expanding Awareness: Comparing Location, Keyword, and Network Filtering Methods to Collect Hyperlocal Social Media Data

Grace¹,

Halse²,

Aurite³

et al. 2019

Proceedings of the Annual Hawaii International Conference on System Sciences

View full text Add to dashboard Cite

Opportunities to collect real-time social media data during a crisis remain limited to location and keyword filtering despite the sparsity of geographic metadata and the tendency of keyword-based methods to capture information posted by remote rather than local users. Here we introduce a third, network filtering method that uses social network ties to infer the location of social media users in a geographic community and collect data from networks of these users during a crisis. In this paper we compare all three methods by analysing the distribution of situational reports of infrastructure damage and service disruption across location, keyword, and network-filtered social media data during a weather emergency. We find that network filtering doubles the number of situational reports collected in real-time compared to location and keyword filtering alone, but that all three methods collect unique reports that can support situational awareness of incidents occurring across a community.

show abstract

“…Its goal is to reduce the duration and impacts of traffic incidents and improve the safety of users. In this direction, two contributions are central in the literature of the last year: [146], where a study about the detection of incidents along the public infrastructure by means of data analysis of social sensor Big Data; and [147], which discusses on the use of Big Data Analytics to predict safety risks and railway accidents. Another work related to this topic is the one presented by Zhu et al in [148], about the resilience of taxi and subway trips from natural disasters using Big Data. Different transport modes, as this survey is not intended to focus strictly on surface transport and mobility.…”

Section: Applications and Related Projectsmentioning

confidence: 99%