Web of Things,
Mobile and Ubiquitous Computing

List of accepted papers :

  • Facebook (A)Live?: Are live social broadcasts really broadcasts?
    Authors: Aravindh Raman, Gareth Tyson and Nishanth Sastry

    Keywords: user generated broadcast, broadcast demographics, live videos

    The era of live-broadcast is back but with two major changes. First, unlike traditional TV broadcasts, content is now streamed over the Internet enabling it to reach a wider audience. And, second, due to various user content generated platforms it has become possible for anyone to become involved, streaming their own content to the world. This emerging trend of going live usually happens via social platforms, where users perform live social broadcasts predominantly from their mobile devices, allowing their friends (and the general public) to engage with the stream in real-time. With the growing popularity of such platforms, the burden on the current Internet infrastructure is therefore expected to multiply. With this in mind, we explore one such prominent platform – Facebook Live. With one month of global data, we explore the characteristics of live social broadcasts, from which we infer a smarter way to alleviate the network burden. We then dissect global and hyper-local properties of the video while on-air, by capturing the geography of the broadcasters, or the users who produce the video and the viewers, or the users who interact with it. Finally, we study the social engagement while the video is live and distinguish the key aspects when the same video goes on-demand. A common theme throughout the paper is that, despite its name, many attributes of Facebook Live deviate from both the concepts of live and broadcast.

  • DeepMove: Predicting Human Mobility with Attentional Recurrent Networks
    Authors: Jie Feng, Yong Li, Chao Zhang, Funing Sun, Fanchao Meng, Ang Guo and Depeng Jin

    Keywords: deep learning, human mobility, location prediction

    Human mobility prediction is of great importance for a wide spectrum of location-based applications. However, predicting mobility is not trivial because of three challenges: 1) the complex sequential transition regularities exhibited with time-dependent and high-order nature; 2) the multi-level periodicity of human mobility; and 3) the heterogeneity and sparsity of the collected trajectory data. In this paper, we propose DeepMove, an attentional recurrent network for mobility prediction from lengthy and sparse trajectories. In DeepMove, we first design a multi-modal embedding recurrent neural network to capture the complicated sequential transitions by jointly embedding the multiple factors that govern the human mobility. Then, we propose a historical attention model with two mechanisms to capture the multi-level periodicity in a principle way, which effectively utilizes the periodicity nature to augment the recurrent neural network for mobility prediction. We perform experiments on three representative real-life mobility datasets, and extensive evaluation results demonstrate that our model outperforms the state-of-the-art models by more than 10%. Moreover, compared with existing simple neural network models, DeepMove provides intuitive explanations into the prediction and sheds light on interpretable mobility prediction.

  • I’ll Be Back: On the Multiple Lives of Users of a Mobile Activity Tracking Application
    Authors: Zhiyuan Lin, Tim Althoff and Jure Leskovec

    Keywords: user engagement, user modeling, reengagement, multiple lives, lifetime, lifespan, activity tracking, activity logging, quantified self, mobile health

    Mobile health applications that track activities, such as exercise, sleep, and diet, are becoming widely used. While these activity tracking applications have the potential to improve our health, user engagement and retention are critical factors for their success. However, long-term user engagement patterns in real-world activity tracking applications are not yet well understood. Here we study user engagement patterns within a mobile physical activity tracking application consisting of 115 million logged activities taken by over a million users over 31 months. Specifically, we show that over 75% of users return and re-engage with the application after prolonged periods of inactivity, no matter the duration of the inactivity. We find a surprising result that the re-engagement usage patterns resemble those of the start of the initial engagement period, rather than being a simple continuation of the end of the initial engagement period. This evidence points to a conceptual model of multiple lives of user engagement, extending the prevalent single life view of user activity. We demonstrate that these multiple lives occur because the users have a variety of different primary intents or goals for using the app. These primary intents are associated with how long each life lasts and how likely the user is to re-engage for a new life. We find evidence for users being more likely to stop using the app once they achieved their primary intent or goal (e.g., weight loss). However, these users might return once their original intent resurfaces (e.g., wanting to lose newly gained weight). We discuss implications of the multiple life paradigm and propose a novel prediction task of predicting the number of lives of a user. Based on insights developed in this work, including a marker of improved primary intent performance, our prediction models achieve 71% ROC AUC. Overall, our research has implications for modeling user re-engagement in health activity tracking applications and has consequences for how notifications, recommendations as well as gamification can be used to increase engagement.

  • Through a Gender Lens: Learning Usage Patterns of Emojis from Large-Scale Android Users
    Authors: Zhenpeng Chen, Xuan Lu, Wei Ai, Huoran Li, Qiaozhu Mei and Xuanzhe Liu
    Presentation moved to track Web of Things, Mobile and Ubiquitous Computing

    Keywords: Emojis, Gender, User profiling, Language-independent

    Based on a large dataset of emoji usage collected from smartphone users across the world, this paper investigates usage of emojis from the gender perspective. We present various interesting findings that evidence a considerable difference in emoji usage between male and female users. Such a difference is significant not just in a statistical sense; it is sufficient for a machine learning algorithm to accurately infer the gender of a user purely based on the emojis used in their messages. In real-world scenarios where gender inference is a necessity, models based on emojis have unique advantages over existing models that are based on the textual or contextual information. Emojis not only provide the language-independent indicator, but also alleviate the risk of leaking private user information through the analysis of text and context.

  • The Cost of Digital Advertisement: Comparing User and Advertiser Views
    Authors: Panagiotis Papadopoulos, Nicolas Kourtellis and Evangelos P. Markatos

    Keywords: cost of mobile advertising, mobile user privacy, mobile personalized advertising

    Digital advertisements are delivered in the form of static images, animations or videos, and their purpose is to deliver a message to desktop or mobile users and promote a product, a service or an idea. Thus, the message’s promoter, or advertiser, pays a monetary cost to buy ad-space in a content provider’s medium (e.g., website) to place their advertisement in the consumer’s display. However, is it only the advertiser who pays for the advertisement delivery? Unlike traditional advertisements in mediums such as newspapers, TVs or radio, in the digital world, the end-users are also paying a cost for the advertisement delivery. Whilst the cost on the advertiser’s side is clearly monetary, on the end-user, it includes both quantifiable costs, such as network requests and transferred bytes, and qualitative costs such as privacy loss to the ad ecosystem. In this study, we aim to increase user awareness regarding the hidden costs of digital advertisement in mobile devices, and compare the user and advertiser views. Specifically, we built OpenDAMP, a transparency tool that passively analyzes users’ web traffic and estimates the costs of advertising for both users and advertisers. Using OpenDAMP, we measure the ad-related costs from both sides in a large, year-long dataset of 1270 real mobile users. Juxtaposing the costs of both sides, we identify a clear imbalance: the advertisers pay several times less to deliver ads to end-users, than the cost paid by the users to download these ads. In addition, the majority of users experience a significant privacy loss to the ad-ecosystem, through the received personalized advertisements and their delivery mechanics.

  • Aladdin: Automating Release of Deep-Link APIs on Android
    Authors: Yun Ma, Ziniu Hu, Yunxin Liu, Tao Xie and Xuanzhe Liu

    Keywords: Deep link, API, Android, Program analysis

    Compared to the Web where each web page has a global URL for external access, a specific “page” inside a mobile app cannot be easily accessed unless the user performs several steps from the landing page of this app. Recently, the concept of “deep link” is expected to be a promising solution and has been advocated by major service providers to enable targeting and opening a specific page of an app externally with an accessible uniform resource identifier. This paper makes a large-scale empirical study to investigate how deep links are really adopted, over 25,000 Android apps. To our surprise, we find that deep links have quite low coverage, e.g., more than 70% and 90% of the apps do not have deep links on Wandoujia and Google Play, respectively. One underlying reason is the mandatory and non-trivial manual efforts of app developers to provide APIs for deep links. We then propose the Aladdin approach along with its supporting tool to help developers practically automate the release of deep-link APIs to access locations inside their apps. Aladdin includes a novel cooperative framework by synthesizing the static analysis and the dynamic analysis while minimally engaging developers’ inputs and configurations, without requiring any coding efforts or additional deployment efforts. We evaluate Aladdin with 579 popular apps and demonstrate its effectiveness and performance.

  • Mile High WiFi: A First Look At In-Flight Internet Connectivity
    Authors: John Rula, Fabian Bustamante, James Newman, Arash Molavi Khaki and David Choffnes

    Keywords: Mobile connectivity, In-flight Internet, Network Performance

    In-Flight Communication (IFC), which can be purchased on a growing number of commercial flights, is often received by consumers with both awe for its mere availability and harsh criticism for its poor performance. Indeed, IFC provides Internet connectivity in some of the most challenging conditions with aircraft traveling at speeds in excess of 500 mph at 30,000 feet above the ground. Yet, while existing services do provide basic Internet accessibility, anecdotal reports rank their quality of service as, at best, poor. In this paper, we present the first characterization of deployed IFC systems. Using over 45 flight-hours of measurements, we profile the performance of IFC across the two dominant access technologies – direct air-to-ground communication (DA2GC) and mobile satellite service (MSS) – over 16 flights and six different airlines. We show that IFC QoS is in large part determined by the high latencies inherent to DA2GC and MSS, with RTTs averaging 200ms and 750ms, respectively, and that these high latencies directly impact the performance of common applications such as web browsing. In addition, we find high link loss rates for IFC – nearly 40% loss at the 90th percentile for MSS – which severely impacts the performance of TCP and other loss-based congestion control protocols. We extend our IFC study exploring the potential of alternative transport protocols and upcoming technology improvements. Using empirically derived emulation we evaluate the performance of the newly released HTTP/2 and QUIC protocols, finding that QUIC is able to improve page load times by as much as 7.9 times. In addition, we find that HTTP/2’s use of multiplexing multiple requests onto a single TCP connection performs up to 4.8x worse than HTTP/1.1 when faced with large numbers of objects. We use network emulation to explore proposed technological improvements to existing IFC systems finding that high link losses account for the largest factor of performance degradation, and that to improving link bandwidth does little to improve the quality of experience for applications such as web browsing.

  • Arrays of (locality-sensitive) Count Estimators (ACE): Anomaly Detection on the Edge
    Authors: Chen Luo and Anshumali Shrivastava

    Keywords: Anomaly Detection, Internet of Things, Edge Computing, Locality Sensitive Hashing

    Anomaly detection is one of the frequent and important subroutines deployed in large-scale data processing applications. Even being a well-studied topic, existing techniques for unsupervised anomaly detection require storing significant amounts of data, which is prohibitive from memory and latency perspectives, especially for small mobile devices which has ultra-low memory budget and limited computational power. In this paper, we propose ACE (Arrays of (locality-sensitive) Count Estimators) algorithm that can be 60x faster than most state-of-the-art unsupervised anomaly detection algorithms. Our experiments show that ACE algorithm has significantly smaller memory footprints (< 4MB in our experiments) which can exploit Level 3 cache of any modern processor. At the core of the ACE algorithm, there is a novel statistical estimator which is derived from the sampling view of Locality Sensitive Hashing (LSH). This view is significantly different and efficient than the widely popular view of LSH for near-neighbor search. We show the superiority of ACE algorithm over 11 popular baselines on 3 benchmark datasets, including the KDD-Cup99 data which is the largest available public benchmark comprising of more than half a million entries with ground truth anomaly labels.