BITS Faculty Publications

Permanent URI for this communityhttp://localhost:4000/handle/123456789/1867

Browse

Filters

2017 - 201932020 - 20253

Settings

Has files: NoSubject: search.filters.subject.Crowdsourcing

Search Results

Now showing 1 - 6 of 6
  • No Thumbnail Available
    Item
    Determining disaster severity through social media analysis: testing the methodology with South East Queensland Flood tweets
    (Elsevier, 2020-01) Goonetilleke, Ashantha
    Social media was underutilised in disaster management practices, as it was not seen as a real-time ground level information harvesting tool during a disaster. In recent years, with the increasing popularity and use of social media, people have started to express their views, experiences, images, and video evidences through different social media platforms. Consequently, harnessing such crowdsourced information has become an opportunity for authorities to obtain enhanced situation awareness data for efficient disaster management practices. Nonetheless, the current disaster-related Twitter analytics methods are not versatile enough to define disaster impacts levels as interpreted by the local communities. This paper contributes to the existing knowledge by applying and extending a well-established data analysis framework, and identifying highly impacted disaster areas as perceived by the local communities. For this, the study used real-time Twitter data posted during the 2010–2011 South East Queensland Floods. The findings reveal that: (a) Utilising Twitter is a promising approach to reflect citizen knowledge; (b) Tweets could be used to identify the fluctuations of disaster severity over time; (c) The spatial analysis of tweets validates the applicability of geo-located messages to demarcate highly impacted disaster zones.
  • No Thumbnail Available
    Item
    Development of a web application through a mobilized crowdsourcing platform to enable participatory risk sensitive urban development
    (AARS, 2025) Goonetilleke, Ashantha
    Flooding is the most frequent and destructive natural disaster currently facing Sri Lanka. Rapid urbanization and changing precipitation patterns are exacerbating the situation, leading to extensive socio-economic damage and disrupting countless lives. Despite the availability of technology-based applications that can raise disaster awareness and improve management, these tools are not fully utilized in Sri Lankan communities. The study addresses the critical issue of insufficient awareness and the lack of formal early flood alert mechanisms within Sri Lankan. Although, recent technological advancements offer opportunities for community to engage in sharing early disaster warnings among their networks, they remain underutilized. The community engagement in disaster management is still minimal, reducing the preparedness and resilience of vulnerable communities. To address this, a platform integrating a crowdsourcing-based mobile application with a web application was developed, aiming to make disaster management and response inclusive through community involvement and advanced remote sensing technologies. A flood vulnerability assessment model was created using 30 years of historical flood data and nine conditioning factors, including topographic features, weather-related variables, hydrological networks, land cover, and soil type, with Sentinel-2 satellite imagery for the Kelaniya watershed area enhancing the model's accuracy. The mobile application facilitates real-time data collection from individuals in flood-prone areas, who can report on flood levels, affected locations, and other critical information. This crowdsourced data undergoes rigorous verification to ensure accuracy. Once validated, the information is visualized on a web application, serving as a vital communication tool for both the community and disaster response authorities. The methodology includes developing the vulnerability assessment model, creating the mobile application with integrated crowdsourcing techniques, and conducting trial workshops to engage the community and validate the platform with the contribution of relevant authorities. Mobilization strategies are proposed based on insights from these community interactions. By prioritizing community participation and utilizing cutting-edge geo-information technologies, this research significantly contributes to building resilient and proactive urban communities in Sri Lanka. The findings demonstrate the substantial potential of combining crowdsourced data with remote sensing to enhance disaster management and community resilience.
  • No Thumbnail Available
    Item
    Task assignment in Crowd sourcing using vector space model
    (International Journal of Pure and Applied Mathematics, 2017) Anand, Vijayalakshmi
    Recently the crowd sourcing has become a well known model for doing different assignments in different field. But there are some challenges and issues. The important issues in crowd sourcing are the task assignment and quality. Assigning task to particular resource is a challenge as most of people are unfamiliar, unknown about crowd sourcing and maximum assignment is done online. We address this issue by finding the experts and assign the task based on their expertization. Here we assumed that expert people will always produce quality work. We used this technique in our social media application which is especially created for faculties .We have used a vector space model for finding experts which is normally used for retrieval of document based on the query in a search engines.
  • No Thumbnail Available
    Item
    Intelligent Task Assignment in a Crowdsourcing Platform
    (Springer, 2018-11) Anand, Vijayalakshmi
    Crowdsourcing is a process of judiciously selecting the right user (worker) from a large pool of online community who could solve the task. The undertaking of jobs by many online users (workers) simultaneously helps solving large-scale computational problems. After completion of the job, monetary reward would be offered to the user who has completed the job satisfactorily or efficiently. The main challenge in crowdsourcing platforms is to assign a task to a user as users are mainly available online and are unknown and unfamiliar to each other. To overcome this challenge, we have proposed a new algorithm for task assignment based on the trustworthiness of online users. Trustworthiness is calculated by using the belief and knowledge values (metrics) of individuals who have shown interest in taking up the task. We have used vector space model to find out that the person is knowledgeable to do the task at hand. The belief value for a user is calculated by using the reputation and the familiarity index of the user on the social media interactions. Tasks would be assigned to all the users whose trust value is above a specific threshold. We have evaluated the proposed algorithm on a social media application that we created for sharing expertise amongst the off-campus faculty colleagues of our university.
  • No Thumbnail Available
    Item
    Reputation-Based Reinforcement Algorithm for Motivation in Crowdsourcing Platform
    (Springer, 2019-07) Anand, Vijayalakshmi
    Crowdsourcing is a well-known model for solving tasks in several organizations in the recent times. While building, the crowdsourcing platform is simple, and its success depends on the amount of individuals taking part in it. We propose a brand new gamification methodology to draw folks to participate within the crowdsourcing platform. Reinforcement algorithm is employed in this gamification method to motivate the people. This reinforcement algorithm can direct a user to participate in some actions that yield maximum reward in a crowdsourcing platform. This gamification technique motivates user to participate in various activities in the crowdsourcing platform. The proposed algorithm is applied on a social media application that has been implemented for faculties to share their research and tutorial experience. We proved that participation of faculties in crowdsourcing platform improved after applying this gamification method.
  • No Thumbnail Available
    Item
    Motivation of participants on the crowdsourcing platform using intelligent agents
    (Research Institute for Intelligent Computer Systems, 2020-03) Anand, Vijayalakshmi
    Crowdsourcing is a model where individuals or organizations receive services from a large group of Internet users including ideas, finances, completing a complex task, etc. Several crowdsourcing websites have failed due to la ck of user participation; hence, the success of crowdsourcing platforms is manifested by the mass of user participation. However, an issue of motivating users to participate in crowdsourcing platform stays challenging. We have proposed a new approach, i.e. , reinforcement learning - based gamification method to motivate users. Gamification has been a practical approach to engaging users in many fields, but still, it needs an improvement in the Crowdsourcing platform. In this paper, the gamification approach is strengthened by a reinforcement learning algorithm. We have created an intelligent agent using the Reinforcement learning algorithm (Q - learning). This agent suggests an optimal action plan that yields maximum reward points to the users for their active pa rticipation in the Crowdsourcing application. Also, its performance is compared with the SARSA algorithm (On - policy learning), which is another Reinforcement learning algorithm.