Web tracking and advertising (WTA) nowadays are ubiquitously performed on the web, continuously compromising users’ privacy. Existing defense solutions, such as widely deployed blocking tools based on filter lists and alternative machine learning based solutions proposed in prior research, have limitations in terms of accuracy and effectiveness. In this work, we propose WTAGRAPH, a web tracking and advertising detection framework based on Graph Neural Networks (GNNs). We first construct an attributed homogenous multi-graph (AHMG) that represents HTTP network traffic, and formulate web tracking and advertising detection as a task of GNN-based edge representation learning and classification in AHMG. We then design four components in WTAGRAPH so that it can (1) collect HTTP network traffic, DOM, and JavaScript data, (2) construct AHMG and extract corresponding edge and node features, (3) build a GNN model for edge representation learning and WTA detection in the transductive learning setting, and (4) use a pre-trained GNN model for WTA detection in the inductive learning setting. We evaluate WTAGRAPH on a dataset collected from Alexa Top 10K websites, and show that WTAGRAPH can effectively detect WTA requests in both transductive and inductive learning settings. Manual verification results indicate that WTAGRAPH can detect new WTA requests that are missed by filter lists and recognize non-WTA requests that are mistakenly labeled by filter lists. Our ablation analysis, evasion evaluation, and real-time evaluation show that WTAGRAPH can have a competitive performance with flexible deployment options in practice.

Crowdsourcing is popular for large-scale data collection and labeling, but a major challenge is on detecting low-quality submissions. Recent studies have demonstrated that behavioral features of workers are highly correlated with data quality and can be useful in quality control. However, these studies primarily leveraged coarsely extracted behavioral features, and did not further explore quality control at the fine-grained level, i.e., the annotation unit level. In this paper, we investigate the feasibility and benefits of using fine-grained behavioral features, which are the behavioral features finely extracted from a worker's individual interactions with each single unit in a subtask, for quality control in crowdsourcing. We design and implement a framework named Fine-grained Behavior-based Quality Control (FBQC) that specifically extracts fine-grained behavioral features to provide three quality control mechanisms: (1) quality prediction for objective tasks, (2) suspicious behavior detection for subjective tasks, and (3) unsupervised worker categorization. Using the FBQC framework, we conduct two real-world crowdsourcing experiments and demonstrate that using fine-grained behavioral features is feasible and beneficial in all three quality control mechanisms. Our work provides clues and implications for helping job requesters or crowdsourcing platforms to further achieve better quality control.

The increased use of machine learning in recent years led to large volumes of data being manually labeled via crowdsourcing microtasks completed by humans. This brought about dehumanization effects, namely, when task requesters overlook the humans behind the task, leading to issues of ethics (e.g., unfair payment) and amplification of human biases, which are transferred into training data and affect machine learning in the real world. We propose a framework that allocates microtasks considering human factors of workers such as demographics and compensation. We deployed our framework to a popular crowdsourcing platform and conducted experiments with 1,919 workers collecting 160,345 human judgments. By routing microtasks to workers based on demographics and appropriate pay, our framework mitigates biases in the contributor sample and increases the hourly pay given to contributors. We discuss potential extensions and how it can promote transparency in crowdsourcing.

Abstract This paper proposes technical solutions to collect, record, and track health vaccination records for children in a developing world context. The problem we address in this paper is very important, and often underappreciated. Our solution consists of two elements: bracelets containing NFC tags (intended to be worn by the children), and NFC enabled Android smartphones (intended to be used by the doctors) in order to manage the vaccine information contained within the bracelets. We use a tattoo design inspired by ethnography for our prototype of the NFC enabled bracelet. The visual representation of the tattoo is printed on the bracelet surface. It conveys an overall picture of the current vaccination status. Furthermore, the tattoo is the central element of the user interface of the Android App that allows the doctors to access, read, and update more detailed information about the child's vaccination status.

In this paper we present the initial results of a pilot study designed to explore the reactions and actions of children who experience a power failure while playing a hybrid physical/digital game. We wanted to see whether we can maintain the engagement of the children with the game if the digital component of the game (a tablet based game) ceases to function and if so whether they will continue from where they left off in the digital game or whether they will start a new round of gameplay. Early results suggests that the power failure and the resultant interruption to gameplay did not hamper the children engagement with the game but provided them with the opportunity to re-engage with the physical elements of the game. This suggests new directions for exploring the design of hybrid physical/digital games.

We present a gaze-based installation enabling two participants to experience cycles of relationship "destroyed" by tunnel vision. The installation comprises a holographic projection screen and two eye-trackers. The trackers allow us to identify the gaze positions and onset of eye contacts. The holographic screen makes it possible to block out the eyesight by projection and to see through without projection. Two participants sitting on both sides of the screen will encounter series of artificial tunnel vision and blindness.

We present an audio installation allowing participants to create sounds by looking at different parts of surfaces or objects in various color and texture. By hacking a desktop eye tracker to track gaze points in 3D space, and deploying a webcam to pick up the hue, saturation and brightness of gazed material, we create an experimental musical instrument that can be played by eye gaze. Users have the freedom of choosing different raw materials and explore ways of seeing as a mean of self-expression to create a unique audio experience.

This paper presents Pirate Island, a role-playing videogame for foreign language learning. Pirate Island utilizes new learning and gameplay mechanics developed through research into the cognitive science of language learning, and the process and impact of immersion experiences. In particular, the immersion experience informs the game's approach to exposing players to content traditionally more advanced than what students would encounter in class. Players complete quests in the detailed virtual world, teaching themselves through exploring and interpreting multiple forms of learning content. The game is targeted toward 10-12 year old children and is being developed to help teach Portuguese children English. At its core, Pirate Island incorporates Rosetta Stone-style tools with role-playing gameplay to create an intrinsically motivating learning experience.

Engaging children born in the digital age with traditional culture practices is a pedagogical and a technological challenge. In this paper we describe Ilha Musical, an interactive panoramic experience designed to foster appreciation of traditional Madeiran cultural practices in children from the island and abroad. The design employs a rhythm game in which children engage in traditional folk music and song while being exposed to visuals of the landscape, architecture, dance and other cultural motifs. We conclude with an eye tracking and scene analysis showing the success of the game in using competition and cooperation as a means of engaging the children with each other as well as with the narrative, the physical display and interface elements.

Modern transportation has changed our lifestyle and allowed for many more options for the daily commute. Particularly in Taiwan, a unique regional phenomenon is that people tend to travel to almost anywhere by scooter. With the intention of replacing the scooter ride for short-distance journeys with walking, we introduce a system called "HappyFeet", which encourages users to walk more with various interactive ways. The user testing demonstrated that the users were enthusiastic about our design and they provided positive feedback as well as some comments for ways to improve.

Previous studies have outlined the advantages of multi-resolution large-area displays over their fixed-resolution counterparts, however the mobility of the focus region has up until the present time received little attention. To study this phenomenon further, we have developed a multi-resolution tabletop display system with a steerable high resolution focus region to compare the performance between steerable and fixed focus region systems under different working scenarios. We have classified these scenarios according to region of interest (ROI) with analogies to different eye movement types (fixed, saccadic, and pursuit ROI). Empirical data gathered during the course of a multi-faceted user study demonstrates that the steerable focus region system significantly outperforms the fixed focus region system. The former is shown to provide enhanced display manipulation and proves especially advantageous in cases where the user must maintain spatial awareness of the display content as is the case in which, within a single session, several regions of the display are to be visited.