Computer Engineering Commons^™

Network Economics-Based Crowdsourcing In Online Social Networks, Natasha S. Kubiak

Electrical and Computer Engineering ETDs

This thesis addresses the challenge of user recruitment by various competing marketing agencies (MAs) in Online Social Networks. A labor economics approach, following the principles of contract theory, is devised to enable MAs to reveal the potential of each participating user to contribute a personalized level of quality and quantity of information to the crowdsourcing process. The MAs objective is to maximize their personal benefit, i.e., total utility obtained, given its budget. The latter optimization problem is formulated as a Generalized Colonel Blotto (GCB) game among the MAs, where each MA aims at incentivizing each user to report its information. …

Optimal Order Assignment With Minimum Wage Consideration (Ooamwc), Hakem Alazmi

Master of Science in Computer Science Theses

While the application of crowdsourcing has increased over the years, the technology experiences various issues during implementation. Examples of some of the issues that affect crowdsourcing include task assignment, profit maximizations, as well as time window issues. In some instances addressing some of the issues results in the other issues being overlooked. An example is when assigning tasks to workers, the profits of the workers might not be considered and this ends up affecting the profit maximization aspect. Various algorithms have been proposed to address the task assignment, profit maximizations, and time window issues. However, these algorithms address the issues …

Changing The Focus: Worker-Centric Optimization In Human-In-The-Loop Computations, Mohammadreza Esfandiari

Dissertations

A myriad of emerging applications from simple to complex ones involve human cognizance in the computation loop. Using the wisdom of human workers, researchers have solved a variety of problems, termed as “micro-tasks” such as, captcha recognition, sentiment analysis, image categorization, query processing, as well as “complex tasks” that are often collaborative, such as, classifying craters on planetary surfaces, discovering new galaxies (Galaxyzoo), performing text translation. The current view of “humans-in-the-loop” tends to see humans as machines, robots, or low-level agents used or exploited in the service of broader computation goals. This dissertation is developed to shift the focus back …

Smart Communities: From Sensors To Internet Of Things And To A Marketplace Of Services, Stephan Olariu, Nirwan Ansari (Editor), Andreas Ahrens (Editor), Cesar Benavente-Preces (Editor)

Computer Science Faculty Publications

Our paper was inspired by the recent Society 5.0 initiative of the Japanese Government that seeks to create a sustainable human-centric society by putting to work recent advances in technology: sensor networks, edge computing, IoT ecosystems, AI, Big Data, robotics, to name just a few. The main contribution of this work is a vision of how these technological advances can contribute, directly or indirectly, to making Society 5.0 reality. For this purpose we build on a recently-proposed concept of Marketplace of Services that, in our view, will turn out to be one of the cornerstones of Society 5.0. Instead of …

Mnews: A Study Of Multilingual News Search Interfaces, Chenjun Ling

Engineering Ph.D. Theses

With the global expansion of the Internet and the World Wide Web, users are becoming increasingly diverse, particularly in terms of languages. In fact, the number of polyglot Web users across the globe has increased dramatically.

However, even such multilingual users often continue to suffer from unbalanced and fragmented news information, as traditional news access systems seldom allow users to simultaneously search for and/or compare news in different languages, even though prior research results have shown that multilingual users make significant use of each of their languages when searching for information online.

Relatively little human-centered research has been conducted to …

Worker Demographics And Earnings On Amazon Mechanical Turk: An Exploratory Analysis, Kotaro Hara, Kristy Milland, Benjamin V. Hanrahan, Chris Callison-Burch, Abigail Adams, Saiph Savage, Jeffrey P. Bigham

Research Collection School Of Computing and Information Systems

Prior research reported that workers on Amazon Mechanical Turk (AMT) are underpaid, earning about $2/h. But the prior research did not investigate the difference in wage due to worker characteristics (e.g., country of residence). We present the first data-driven analysis on wage gap on AMT. Using work log data and demographic data collected via online survey, we analyse the gap in wage due to different factors. We show that there is indeed wage gap; for example, workers in the U.S. earn $3.01/h while those in India earn $1.41/h on average.

Spam Elimination And Bias Correction : Ensuring Label Quality In Crowdsourced Tasks., Lingyu Lyu

Electronic Theses and Dissertations

Crowdsourcing is proposed as a powerful mechanism for accomplishing large scale tasks via anonymous workers online. It has been demonstrated as an effective and important approach for collecting labeled data in application domains which require human intelligence, such as image labeling, video annotation, natural language processing, etc. Despite the promises, one big challenge still exists in crowdsourcing systems: the difficulty of controlling the quality of crowds. The workers usually have diverse education levels, personal preferences, and motivations, leading to unknown work performance while completing a crowdsourced task. Among them, some are reliable, and some might provide noisy feedback. It is …

Smartphone Sensing Meets Transport Data: A Collaborative Framework For Transportation Service Analytics, Yu Lu, Archan Misra, Wen Sun, Huayu Wu

Research Collection School Of Computing and Information Systems

We advocate for and introduce TRANSense, a framework for urban transportation service analytics that combines participatory smartphone sensing data with city-scale transportation-related transactional data (taxis, trains etc.). Our work is driven by the observed limitations of using each data type in isolation: (a) commonly-used anonymous city-scale datasets (such as taxi bookings and GPS trajectories) provide insights into the aggregate behavior of transport infrastructure, but fail to reveal individual-specific transport experiences (e.g., wait times in taxi queues); while (b) mobile sensing data can capture individual-specific commuting-related activities, but suffers from accuracy and energy overhead challenges due to usage artefacts and lack …

Droidnet: An Android Application Security Framework Through Crowdsourcing, Pulkit Rustgi, Bilal Ahmed, Mansi Shah

Capstone Design Expo Posters

In the current Android architecture, users have to decide whether an app is safe to use or not by themselves. Savvy users can make correct decisions to avoid unnecessary privacy breaches, however most users are not capable or do not care to make impactful decisions. To assist those users, we propose DroidNet, an Android permission control framework based on crowdsourcing. In this framework, DroidNet runs new apps and their permissions initially, and then collects data based on each individual user’s settings in regards to each permission unique to every installed app. After collecting each user’s data, DroidNet provides recommendations on …

Video Annotation By Crowd Workers With Privacy-Preserving Local Disclosure, Apeksha Dipak Kumavat

Open Access Theses

Advancements in computer vision are still not reliable enough for detecting video content including humans and their actions. Microtask crowdsourcing on task markets such as Amazon Mechnical Turk and Upwork can bring humans into the loop. However, engaging crowd workers to annotate non-public video footage risks revealing the identities of people in the video who may have a right to anonymity.

This thesis demonstrates how we can engage untrusted crowd workers to detect behaviors and objects, while robustly concealing the identities of all faces. We developed a web-based system that presents obfuscated videos to crowd workers, and provides them with …

Design Of Decision Support Tools For The Quality Assessment Of Illegal Dumping Notifications Based On Crowd-Sourced Data, Jan Brus, Jakub Vrkoč, Miroslav Kubásek

International Congress on Environmental Modelling and Software

Illegal dumping has become an increasingly significant environmental problem throughout the Czech Republic and also in Prague. The waste is disposed in areas such as vacant lots, along roadways, alleys, city and county parks, ravines, construction sites. The challenge for cities dealing with illegal dumping is that it is tough to identify when it will happen, where it will occur, and how much will be dumped. The paper is therefore focused on designing a decision support tool, which uses crowdsourcing data to cope with this problem as the management of illegal dumps can be built upon citizen reports via the …

Using Web Content For Informing Water Management In Snow-Dominated Catchments, M. Giuliani, R. Fedorov, A. Castelleti, P. Fraternali

International Congress on Environmental Modelling and Software

Snow accumulation and melting are fundamental components of the hydrologic cycle in many water systems across the world. In such contexts, improving snow monitoring can be extremely valuable in a variety of operational contexts, such as avalanche protection, medium to long-term streamflow forecast, and drought risk management. Despite recent advances in environmental monitoring systems, continuous snow monitoring systems able to collect data at high spatial and temporal resolution are not well established yet. The unprecedented availability of user generated data on the Web is opening new opportunities for enhancing real-time monitoring and modeling of environmental systems based on data that …

Crowdsourcing Management Education Assessment, Owen P. Hall Jr, Charla Griffy-Brown

Journal of International Technology and Information Management

Assessment is now at the center of the new business education zeitgeist. This focus is the direct result of feedback from the business community regarding the growing gap between their needs and graduates from many business schools. Recently this divide has fallen under even closer scrutiny because of increasing student debt and the growing controversy over return-on- investment. Today business leaders are looking for web-savvy, problem-solving graduates. To this end, AACSB and regional accrediting bodies are calling for the adoption of comprehensive collaborative learning strategies to better align graduates’ skill sets with the real needs of business. Crowdsourcing, which is …

State And Trends In Mobile Observation Applications, Denis Havlik, Gerald Schimak

International Congress on Environmental Modelling and Software

The stellar growth of the smartphones and nearly gapless mobile network coverage in urban and suburban areas has widely extended the potential of the citizens' observatories. The possibility to easily record observations made by mobile citizens, and to automatically enrich this information using the built-in and external sensors sounds like a dream come true of the scientists and decision makers alike. However, in 2013 only a tiny portion of the potential users really participated in the citizen observation programs and the usability of the received information is often below expectations. The learning curve is often too high, sensor quality too …

Involving Citizens Into Mapping Of Illegal Landfills And Other Civic Issues In The Czech Republic, Miroslay Kubásek, Jiři Hřebíček

International Congress on Environmental Modelling and Software

Today's smartphones can unlock the full potential of crowdsourcing and take eParticipation to a new level. Users are allowed to transparently contribute to complex and novel problem solving. Engagement of citizens is still challenging but the proliferation of smartphones with geolocation have made it easier than before. The paper introduces the environmental project called ZmapujTo.cz. This project is primarily intended to fight illegal waste dumps in the Czech Republic. The idea is to use the potential awareness of the broader public about the environmental and economic drawbacks of illegal landfills. We developed a more efficient version of the web portal …

Crowdsourcing In Early Warning Systems, Ulrich Meissen, Frank Fuchs-Kittowski

International Congress on Environmental Modelling and Software

The use of mobile devices as an effective and targeted way for alerting the public in cases of disasters has become an important part of future infrastructures for early warning and disaster management. In contrast to classical alert approaches such as TV, Radio and sirens that are offering solely a one-directional communication the use of smart phones opens new potentials such as feedback mechanisms that support more precise warnings and adapted response actions. In this context crowdsourcing techniques show a high potential as an effective measure to meliorate the data basis for predictions and augment warnings. This paper discusses the …

A Bayesian Maximum Entropy Scheme For The Assimilation Of Mobile Recordings With Simulations Of Urban Micrometeorological Data, Uwe Schlink, Gabi Fischer

International Congress on Environmental Modelling and Software

This paper proposes a framework for assimilating urban temperature measurements with simulations of an urban micrometeorological model. Data assimilation, a technique that incorporates observations into a computer model of a real system, is commonly applied in global and regional weather forecasting and an emerging issue in urban meteorological modelling. For that purpose, we suggest applying a novel approach, the Spatiotemporal Epistemic Knowledge Synthesis (SEKS). It combines simulations of a thermodynamic urban climate model, as general knowledge base, with a model output statistics (MOS) of observations, as site-specific knowledge base, by means of Bayesian Maximum Entropy (BME) inference resulting in posterior …

Sew-Ing A Simple Endorsement Web To Incentivize Trustworthy Participatory Sensing, T. Luo, S. Kanhere, Hwee-Pink Tan

Research Collection School Of Computing and Information Systems

Two crucial issues to the success of participatory sensing are (a) how to incentivize the large crowd of mobile users to participate and (b) how to ensure the sensing data to be trustworthy. While they are traditionally being studied separately in the literature, this paper proposes a Simple Endorsement Web (SEW) to address both issues in a synergistic manner. The key idea is (a) introducing a social concept called nepotism into participatory sensing, by linking mobile users into a social “web of participants” with endorsement relations, and (b) overlaying this network with investment-like economic implications. The social and economic layers …

A Crowdsourcing Approach To Labelling A Mood Induced Speech Corpus, John Snel, Alexey Tarasov, Charlie Cullen, Sarah Jane Delany

Conference papers

This paper demonstrates the use of crowdsourcing to accumulate ratings from na ̈ıve listeners as a means to provide labels for a naturalistic emotional speech dataset. In order to do so, listening tasks are performed with a rating tool, which is delivered via the web. The rating requirements are based on the classical dimensions, activation and evaluation, presented to the participant as two discretised 5-point scales. Great emphasis is placed on the participant’s overall understanding of the task, and on the ease-of-use of the tool so that labelling accuracy is reinforced. The accumulation process is ongoing with a goal to …