Mobile devices have become an increasingly ubiquitous part of our everyday life. We use mobile services to perform a broad range of tasks (e.g., booking travel or conducting remote office work), leading to often lengthy interactions with several distinct apps and services. Existing mobile systems handle mostly simple user needs, where a single app is taken as the unit of interaction. To understand users’ expectations and to provide context-aware services, it is important to model users’ interactions with their performed task in mind. To provide a comprehensive picture of common mobile tasks, we first conduct a small-scale user study to understand annotated mobile tasks in-depth, while we demonstrate that by using a set of features (temporal, similarity, and log sequence), we can identify if a pair of app usage belong to the same task effectively. Secondly, the proposed best task detection model is applied to a large-scale data set of commercial mobile app usage logs to infer characteristics of complex (multi-app) mobile tasks in the wild. By applying an unsupervised learning framework, we discover common mobile task types that span multiple apps based on various extracted characteristics. We observe that users generally perform 17 common tasks with 47 sub-tasks, ranging from “social media browsing” to “dining out” and “family entertainments”. Finally, we demonstrate that we can predict the next complex mobile task that users are likely to perform by leveraging features from the historically inferred mobile tasks and user contexts. Our work facilitates an in-depth understanding of mobile tasks at scale, enabling applications for promoting task-aware services.

User engagement is crucial to the long-term success of a mobile app. Several metrics, such as dwell time, have been used for measuring user engagement. However, how to effectively predict user engagement in the context of mobile apps is still an open research question. For example, do the mobile usage contexts (e.g., time of day) in which users access mobile apps impact their dwell time? Answers to such questions could help mobile operating system and publishers to optimize advertising and service placement. In this article, we first conduct an empirical study for assessing how user characteristics, temporal features, and the short/long-term contexts contribute to gains in predicting users’ app dwell time on the population level. The comprehensive analysis is conducted on large app usage logs collected through a mobile advertising company. The dataset covers more than 12K anonymous users and 1.3 million log events. Based on the analysis, we further investigate a novel mobile app engagement prediction problem—can we predict simultaneously what app the user will use next and how long he/she will stay on that app? We propose several strategies for this joint prediction problem and demonstrate that our model can improve the performance significantly when compared with the state-of-the-art baselines. Our work can help mobile system developers in designing a better and more engagement-aware mobile app user experience.

Mobile devices have become an increasingly ubiquitous part of our everyday life. We use mobile services to perform a broad range of tasks (e.g. booking travel or office work), leading to often lengthy interactions within distinct apps and services. Existing mobile systems handle mostly simple user needs, where a single app is taken as the unit of interaction. To understand users' expectations and to provide context-aware services, it is important to model users' interactions in the task space. In this work, we first propose and evaluate a method for the automated segmentation of users' app usage logs into task units. We focus on two problems: (i) given a sequential pair of app usage logs, identify if there exists a task boundary, and (ii) given any pair of two app usage logs, identify if they belong to the same task. We model these as classification problems that use features from three aspects of app usage patterns: temporal, similarity, and log sequence. Our classifiers improve on traditional timeout segmentation, achieving over 89% performance for both problems. Secondly, we use our best task classifier on a large-scale data set of commercial mobile app usage logs to identify common tasks. We observe that users' performed common tasks ranging from regular information checking to entertainment and booking dinner. Our proposed task identification approach provides the means to evaluate mobile services and applications with respect to task completion.

Smartphones utilize context signals, such as time and location, to predict users' app usage tailored to individual users. To be effective, such personalization relies on access to sufficient information about each user's behavioral habits. For new users, the behavior information may be sparse or non-existent. To handle these cases, app category usage prediction approaches can employ signals from users who are similar along one or more dimensions, i.e., those in the same cohort. In this paper, we describe a characterization and evaluation of the use of such cohort modeling to enhance app category usage prediction. We experiment with pre-defined cohorts from three taxonomies - demographics, psychographics, and behavioral patterns - independently and in combination. We also evaluate various approaches to assign users into the corresponding cohorts. We show, through extensive experiments with large-scale mobile app usage logs from a mobile advertising company, that leveraging cohort behavior can yield significant prediction performance gains than when using the personalized signals at the individual prediction level. In addition, compared to the personalized model, the cohort-based approach can significantly alleviate the cold-start problem, achieving strong predictive performance even with limited amount of user interactions.

With mobile devices, users are taking ever-growing numbers of photos every day. These photos are uploaded to social sites such as Facebook and Flickr, often automatically. Yet, the portion of these uploaded photos being publicly shared is low, and on a constant decline. Deciding which photo to share takes considerable time and attention, and many users would rather forfeit the social interaction and engagement than sift through their piles of uploaded photos. In this paper, we introduce a novel task of recommending socially-engaging photos to their creators for public sharing. This will turn a tedious manual chore into a quick, software-assisted process. We provide extensive analysis over a large-scale dataset from the Flickr photo sharing website, which reveals some of the traits of photo sharing in such sites. Additionally, we present a ranking algorithm for the task that comprises three steps:(a) grouping of near-duplicate photos;(b) ranking the photos in each group by their "shareability"; and(c) ranking the groups by their likelihood to contain a shareable photo. A large-scale experiment allows us to evaluate our algorithm and show its benefits compared to competitive baselines and algorithmic alternatives.

A significant portion of web search queries directly refers to named entities. Search engines explore various ways to improve the user experience for such queries. We suggest augmenting search results with trivia facts about the searched entity. Trivia is widely played throughout the world, and was shown to increase users' engagement and retention.

In this paper, we study multi-click queries - queries for which more than one click is performed by the same user within the same query session. Such queries may reflect a more complex information need, which leads the user to examine a variety of results. We present a comprehensive analysis that reveals unique characteristics of multi-click queries, in terms of their syntax, lexical domains, contextual properties, and returned search results page. We also show that a basic classifier for predicting multi-click queries can reach an accuracy of 75% over a balanced dataset. We discuss the implications of our findings for the design of Web search tools.

Social media gives voice to the people, but also opens the door to low-quality contributions, which degrade the experience for the majority of users. To address the latter issue, the prevailing solution is to rely on the 'wisdom of the crowds' to promote good content (e.g., via votes or 'like' buttons), or to downgrade bad content. Unfortunately, such crowd feedback may be sparse, subjective, and slow to accumulate. In this pa- per, we investigate the effects, on the users, of automatically filtering question-answering content, using a combination of syntactic, semantic, and social signals. Using this filtering, a large-scale experiment with real users was performed to mea- sure the resulting engagement and satisfaction. To our knowledge, this experiment represents the first reported large-scale user study of automatically curating social media content in real time. Our results show that automated quality filtering indeed improves user engagement, usually aligning with, and often outperforming, crowd-based quality judgments.

We present a collection of over 15,000 queries, issued to commercial web search engines, whose answer is a single fact. The collection was produced based on queries landing on questions within a large community question answering website, each with a best answer no longer than 3 words and an explicit reference to a Wikipedia page. We describe the collection generation process and provide a variety of descriptive characteristics, demonstrating the collection?s uniqueness compared to existing datasets and its potential use for research of factoid question answering and retrieval.

No abstract available.

With mobile devices, web search is no longer limited to specific locations. People conduct search from practically anywhere, including at home, at work, when traveling and when on vacation. How should this influence search tools and web services? In this paper, we argue that information needs are affected by the familiarity of the environment. To formalize this idea, we propose a new contextualization model for activities on the web. The model distinguishes between a search from a familiar place (F-search) and a search from an unfamiliar place (U-search). We formalize the notion of familiarity, and propose a method to identify familiar places. An analysis of a query log of millions of users, demonstrates the differences between search activities in familiar and in unfamiliar locations. Our novel take on search contextualization has the potential to improve web applications, such as query autocompletion and search personalization.

What makes a good question recommendation system for community question-answering sites? First, to maintain the health of the ecosystem, it needs to be designed around answerers, rather than exclusively for askers. Next, it needs to scale to many questions and users, and be fast enough to route a newly-posted question to potential answerers within the few minutes before the asker's patience runs out. It also needs to show each answerer questions that are relevant to his or her interests. We have designed and built such a system for Yahoo! Answers, but realized, when testing it with live users, that it was not enough.

Community-based Question Answering (CQA) sites, such as Yahoo! Answers, Baidu Knows, Naver, and Quora, have been rapidly growing in popularity. The resulting archives of posted answers to questions, in Yahoo! Answers alone, already exceed in size 1 billion, and are aggressively indexed by web search engines. In fact, a large number of search engine users benefit from these archives, by finding existing answers that address their own queries. This scenario poses new challenges and opportunities for both search engines and CQA sites. To this end, we formulate a new problem of predicting the satisfaction of web searchers with CQA answers. We analyze a large number of web searches that result in a visit to a popular CQA site, and identify unique characteristics of searcher satisfaction in this setting, namely, the effects of query clarity, query-to-question match, and answer quality. We then propose and evaluate several approaches to predicting searcher satisfaction that exploit these characteristics. To the best of our knowledge, this is the first attempt to predict and validate the usefulness of CQA archives for external searchers, rather than for the original askers. Our results suggest promising directions for improving and exploiting community question answering services in pursuit of satisfying even more Web search queries.

A typical disaster recovery system will have mirrored storage at a site that is geographically separate from the main operational site. In many cases, communication between the local site and the backup repository site is performed over a network which is inherently slow, such as a WAN, or is highly strained, for example due to a whole-site disaster recovery operation.The goal of this work is to alleviate the performance impact of the network in such a scenario, and to do so using machine learning techniques. We focus on two main areas, prefetching and read-ahead size determination. In both cases we significantly improve the performance of the system.Our main contributions are as follows: We introduce a theoretical model of the system and the problem we are trying to solve and bound the gain from prefetching techniques. We construct two frequent pattern mining algorithms and use them for prefetching. A framework for controlling and combining multiple prefetch algorithms is presented as well. These algorithms, as well as various simple prefetch algorithms, are compared on a simulation environment. We introduce a novel algorithm for determining the amount of read ahead on such a system that is based on intuition from online competitive analysis and on regression techniques. The significant positive impact of this algorithm is demonstrated on IBM's FastBack system.Much of our improvements have been applied with little or no modification of the current implementation's internals. We therefore feel confident in stating that the techniques are general and are likely to have applications elsewhere.

Code coverage is a common aid in the testing process. It is generally used for marking the source code segments that were executed and, more importantly, those that were not executed.

In constrained clustering it is common to model the pairwise constraints as edges on the graph of observations. Using results from graph theory, we analyze such constraint graphs in two contexts, both of immediate value to practitioners. First, we explore the issue of constraint noise under several intuitive noise models. We apply results from random graph theory, which facilitate the analysis of finite-sized graphs and realistic data partitions and noise levels, to obtain a quantification of the effect noisy edges may have on any constrained clustering algorithm under a set of commonly-used assumptions. We also demonstrate the dangers in the common practice of connected-component constraint set augmentation, when used in the presence of noise. Second, we describe two practical randomized algorithms that estimate the number of induced clusters using only a small number of constraints. We conclude with an experimental evaluation that shows the effect of noise on common UCI data sets, as well as some aspects of the behavior of our algorithms.

This work tries to answer the question of what makes a query difficult. It addresses a novel model that captures the main components of a topic and the relationship between those components and topic difficulty. The three components of a topic are the textual expression describing the information need (the query or queries), the set of documents relevant to the topic (the Qrels), and the entire collection of documents. We show experimentally that topic difficulty strongly depends on the distances between these components. In the absence of knowledge about one of the model components, the model is still useful by approximating the missing component based on the other components. We demonstrate the applicability of the difficulty model for several uses such as predicting query difficulty, predicting the number of topic aspects expected to be covered by the search results, and analyzing the findability of a specific domain.

We introduce a novel active-learning scenario in which a user wants to work with a learning algorithm to identify useful anomalies. These are distinguished from the traditional statistical definition of anomalies as outliers or merely ill-modeled points. Our distinction is that the useful- ness of anomalies is categorized subjectively by the user. We make two additional assumptions. First, there exist extremely few useful anoma- lies to be hunted down within a massive dataset. Second, both useful and useless anomalies may sometimes exist within tiny classes of similar anomalies. The challenge is thus to identify "rare category" records in an unlabeled noisy set with help (in the form of class labels) from a human expert who has a small budget of datapoints that they are prepared to cat- egorize. We propose a technique to meet this challenge, which assumes a mixture model fit to the data, but otherwise makes no assumptions on the particular form of the mixture components. This property promises wide applicability in real-life scenarios and for various statistical mod- els. We give an overview of several alternative methods, highlighting their strengths and weaknesses, and conclude with a detailed empirical analysis. We show that our method can quickly zoom in on an anomaly set containing a few tens of points in a dataset of hundreds of thousands.

We focus on the problem of efficient learning of dependency trees. It is well-known that given the pairwise mutual information coefficients, a minimum-weight spanning tree algorithm solves this problem exactly and in polynomial time. However, for large data-sets it is the construc- tion of the correlation matrix that dominates the running time. We have developed a new spanning-tree algorithm which is capable of exploiting partial knowledge about edge weights. The partial knowledge we main- tain is a probabilistic confidence interval on the coefficients, which we derive by examining just a small sample of the data. The algorithm is able to flag the need to shrink an interval, which translates to inspec- tion of more data for the particular attribute pair. Experimental results show running time that is near-constant in the number of records, with- out significant loss in accuracy of the generated trees. Interestingly, our spanning-tree algorithm is based solely on Tarjan’s red-edge rule, which is generally considered a guaranteed recipe for bad performance.

Article Free Access Share on Accelerating exact k-means algorithms with geometric reasoning Authors: Dan Pelleg School of Computer Science, Carnegie Mellon University School of Computer Science, Carnegie Mellon UniversityView Profile , Andrew Moore School of Computer Science, Carnegie Mellon University School of Computer Science, Carnegie Mellon UniversityView Profile Authors Info & Claims KDD '99: Proceedings of the fifth ACM SIGKDD international conference on Knowledge discovery and data miningAugust 1999 Pages 277–281https://doi.org/10.1145/312129.312248Published:01 August 1999Publication History 196citation2,139DownloadsMetricsTotal Citations196Total Downloads2,139Last 12 Months555Last 6 weeks42 Get Citation AlertsNew Citation Alert added!This alert has been successfully added and will be sent to:You will be notified whenever a record that you have chosen has been cited.To manage your alert preferences, click on the button below.Manage my AlertsNew Citation Alert!Please log in to your account Save to BinderSave to BinderCreate a New BinderNameCancelCreateExport CitationPublisher SiteeReaderPDF

No abstract available.