1. CONTINUOUS TOP-K MONITORING ON DOCUMENT STREAMS
Abstract: The efficient processing of document streams plays an important role in many information filtering systems. Emerging applications, such as news update filtering and social network notifications, demand presenting end-users with the most relevant content to their preferences. In this work, user preferences are indicated by a set of keywords. A central server monitors the document stream and continuously reports to each user the top-k documents that are most relevant to her keywords. Our objective is to support large numbers of users and high stream rates, while refreshing the top-k results almost instantaneously. Our solution abandons the traditional frequency-ordered indexing approach. Instead, it follows an identifier-ordering paradigm that suits better the nature of the problem. When complemented with a novel, locally adaptive technique, our method offers (i) proven optimality the number of considered queries per stream event, and (ii) an order of magnitude shorter response time (i.e., time to refresh the query results) than the current state-of-the-art.
2. PREDICTING STUDENT ACTIONS IN A PROCEDURAL TRAINING ENVIRONMENT
Abstract: Data mining is known to have a potential for predicting user performance. However, there are few studies that explore its potential for predicting student behavior in a procedural training environment. This paper presents a collective student model, which is built from past student logs. These logs are firstly grouped into clusters. Then an extended automaton is created for each cluster based on the sequences of events found in the cluster logs. The main objective of this model is to predict the actions of new students for improving the tutoring feedback provided by an intelligent tutoring system. The proposed model has been validated using student logs collected in a 3D virtual laboratory for teaching biotechnology. As a result of this validation, we concluded that the model can provide reasonably good predictions and can support tutoring feedback that is better adapted to each student type.
3. DYNAMIC FACET ORDERING FOR FACETED PRODUCT SEARCH ENGINES
Abstract: Faceted browsing is widely used in Web shops and product comparison sites. In these cases, a fixed ordered list of facets is often employed. This approach suffers from two main issues. First, one needs to invest a significant amount of time to devise an effective list. Second, with a fixed list of facets it can happen that a facet becomes useless if all products that match the query are associated to that particular facet. In this work, we present a framework for dynamic facet ordering in e-commerce. Based on measures for specificity and dispersion of facet values, the fully automated algorithm ranks those properties and facets on top that lead to a quick drill-down for any possible target product. In contrast to existing solutions, the framework addresses e-commerce specific aspects, such as the possibility of multiple clicks, the grouping of facets by their corresponding properties, and the abundance of numeric facets. In a large-scale simulation and user study, our approach was, in general, favorably compared to a facet list created by domain experts, a greedy approach as baseline, and a state-of-the-art entropy-based solution.
4. TEMPORAL TASK SCHEDULING WITH CONSTRAINED SERVICE DELAY FOR PROFIT MAXIMIZATION IN HYBRID CLOUDS
Abstract: As cloud computing is becoming growingly popular, consumers’ tasks around the world arrive in cloud data centers. A private cloud provider aims to achieve profit maximization by intelligently scheduling tasks while guaranteeing the service delay bound of delay-tolerant tasks. However, the aperiodicity of arrival tasks brings a challenging problem of how to dynamically schedule all arrival tasks given the fact that the capacity of a private cloud provider is limited. Previous works usually provide an admission control to intelligently refuse some of arrival tasks. Nevertheless, this will decrease the throughput of a private cloud, and cause revenue loss. This paper studies the problem of how to maximize the profit of a private cloud in hybrid clouds while guaranteeing the service delay bound of delay-tolerant tasks. We propose a profit maximization algorithm (PMA) to discover the temporal variation of prices in hybrid clouds. The temporal task scheduling provided by PMA can dynamically schedule all arrival tasks to execute in private and public clouds. The sub problem in each iteration of PMA is solved by the proposed hybrid heuristic optimization algorithm, simulated annealing particle swarm optimization (SAPSO). Besides, SAPSO is compared with existing baseline algorithms. Extensive simulation experiments demonstrate that the proposed method can greatly increase the throughput and the profit of a private cloud while guaranteeing the service delay bound.
5. AN ITERATIVE CLASSIFICATION SCHEME FOR SANITIZING LARGE-SCALE DATASETS
Abstract: Cheap ubiquitous computing enables the collection of massive amounts of personal data in a wide variety of domains. Many organizations aim to share such data while obscuring features that could disclose personally identifiable information. Much of this data exhibits weak structure (e.g., text), such that machine learning approaches have been developed to detect and remove identifiers from it. While learning is never perfect, and relying on such approaches to sanitize data can leak sensitive information, a small risk is often acceptable. Our goal is to balance the value of published data and the risk of an adversary discovering leaked identifiers. We model data sanitization as a game between 1) a publisher who chooses a set of classifiers to apply to data and publishes only instances predicted as non-sensitive and 2) an attacker who combines machine learning and manual inspection to uncover leaked identifying information. We introduce a fast iterative greedy algorithm for the publisher that ensures a low utility for a resource-limited adversary. Moreover, using five text data sets we illustrate that our algorithm leaves virtually no automatically identifiable sensitive instances for a state-of-the-art learning algorithm, while sharing over 93% of the original data, and completes after at most 5 iterations.
6. COMPUTING SEMANTIC SIMILARITY OF CONCEPTS IN KNOWLEDGE GRAPHS
Abstract: This paper presents a method for measuring the semantic similarity between concepts in Knowledge Graphs (KGs) such as WordNet and DBpedia. Previous work on semantic similarity methods have focused on either the structure of the semantic network between concepts (e.g. path length and depth), or only on the Information Content (IC) of concepts. We propose a semantic similarity method, namely wpath, to combine these two approaches, using IC to weight the shortest path length between concepts. Conventional corpus-based IC is computed from the distributions of concepts over textual corpus, which is required to prepare a domain corpus containing annotated concepts and has high computational cost. As instances are already extracted from textual corpus and annotated by concepts in KGs, graph-based IC is proposed to compute IC based on the distributions of concepts over instances. Through experiments performed on well known word similarity datasets, we show that the wpath semantic similarity method has produced statistically significant improvement over other semantic similarity methods. Moreover, in a real category classification evaluation, the wpath method has shown the best performance in terms of accuracy and F score.
7. INFLUENCE MAXIMIZATION IN TRAJECTORY DATABASES
ABSTRACT:
In this paper, we study a novel problem of influence maximization in trajectory databases that is very useful in precise location-aware advertising. It finds k best trajectories to be attached with a given advertisement and maximizes the expected influence among a large group of audience. We show that the problem is NP-hard and propose both exact and approximate solutions to find the best set of trajectories. In the exact solution, we devise an expansion-based framework that enumerates trajectory combinations in a best-first manner and propose three types of upper bound estimation techniques to facilitate early termination. In addition, we propose a novel trajectory index to reduce the influence calculation cost. To support large k, we propose a greedy solution with an approximation ratio of (1-1/e), whose performance is further optimized by a new proposed cluster-based method. We also propose a threshold method that can support any approximation ratio ∈ (0, 1]. In addition, we extend our problem to support the scenario when there are a group of advertisements. In our experiments, we use real datasets to construct user profiles, motion patterns and trajectory databases. The experimental results verified the efficiency of our proposed methods.
8. INFLUENTIAL NODE TRACKING ON DYNAMIC SOCIAL NETWORK: AN INTERCHANGE GREEDY APPROACH
Abstract: As both social network structure and strength of influence between individuals evolve constantly, it requires to track the influential nodes under a dynamic setting. To address this problem, we explore the Influential Node Tracking (INT) problem as an extension to the traditional Influence Maximization problem (IM) under dynamic social networks. While Influence Maximization problem aims at identifying a set of k nodes to maximize the joint influence under one static network, INT problem focuses on tracking a set of influential nodes that keeps maximizing the influence as the network evolves. Utilizing the smoothness of the evolution of the network structure, we propose an efficient algorithm, Upper Bound Interchange Greedy (UBI) and a variant, UBI+. Instead of constructing the seed set from the ground, we start from the influential seed set we find previously and implement node replacement to improve the influence coverage. Furthermore, by using a fast update method by calculating the marginal gain of nodes, our algorithm can scale to dynamic social networks with millions of nodes. Empirical experiments on three real large-scale dynamic social networks show that our UBI and its variants, UBI+ achieves better performance in terms of both influence coverage and running time.
9. PERSONAL WEBREVISITATION BY CONTEXT & CONTENT KEYWORD WITH RELEVANCE FEEDBACK
ABSTRACT:
Getting back to previously viewed web pages is a common yet uneasy task for users due to the large volume of personally accessed information on the web. This paper leverages human’s natural recall process of using episodic and semantic memory cues to facilitate recall, and presents a personal web revisitation technique called WebPagePrev through context and content keywords. Underlying techniques for context and content memories’ acquisition, storage, decay, and utilization for page re-finding are discussed. A relevance feedback mechanism is also involved to tailor to individual’s memory strength and revisitation habits. Our 6-month user study shows that:
• Compared with the existing web revisitation tool Memento, History List Searching method, and Search Engine method,
the proposed WebPagePrev delivers the best re-finding quality in finding rate (92.10%), average F1-measure (0.4318) and average rank error (0.3145).
• Our dynamic management of context and content memories including decay and reinforcement strategy can mimic users’ retrieval and recall mechanism. With relevance feedback, the finding rate of WebPagePrev increases by 9.82%, average F1-measure increases by 47.09%, and average rank error decreases by 19.44% compared to stable memory management strategy.Among time, location, and activity context factors in WebPagePrev, activity is the best recall cue, and context+content based re-findingdelivers the best performance, compared to context based re-finding and content based re-finding.
10. PPRANK: ECONOMICALLY SELECTING INITIAL USERS FOR INFLUENCE MAXIMIZATION IN SOCIAL NETWORKS.
Abstract: This paper focuses on seeking a new heuristic scheme for an influence maximization problem in social networks: how to economically select a subset of individuals (so-called seeds) to trigger a large cascade of further adoptions of a new behavior based on a contagion process. Most existing works on selection of seeds assumed that the constant number k seeds could be selected, irrespective of the intrinsic property of each individual’s different susceptibility of being influenced (e.g., it may be costly to persuade some seeds to adopt a new behavior). In this paper, a price-performance-ratio inspired heuristic scheme, PPRank, is proposed, which investigates how to economically select seeds within a given budget and meanwhile try to maximize the diffusion process. Our paper’s contributions are threefold. First, we explicitly characterize each user with two distinct factors: the susceptibility of being influenced (SI) and influential power (IP) representing the ability to actively influence others and formulate users’ SIs and IPs according to their social relations, and then, a convex price-demand curve-based model is utilized to properly convert each user’s SI into persuasion cost (PC) representing the cost used to successfully make the individual adopt a new behavior. Furthermore, a novel cost-effective selection scheme is proposed, which adopts both the price performance ratio (PC-IP ratio) and user’s IP as an integrated selection criterion and meanwhile explicitly takes into account the overlapping effect; finally, simulations using both artificially generated and real-trace network data illustrate that, under the same budgets, PPRank can achieve larger diffusion range than other heuristic and brute-force greedy schemes without taking users’ persuasion costs into account.
11. PUBLIC INTEREST ANALYSIS
BASED ON IMPLICIT FEEDBACK OF IPTV USERS
ABSTRACT: Modern
information systems make it increasingly easy to gain more insight into the
public interest, which is becoming more and more important in diverse public
and corporate activities and processes. The disadvantage of existing research
that focuses on mining the information from social networks and online
communities is that it doesn’t uniformly represent all population groups and
that the content can be subjected to self-censoring or curation. In this paper
we propose and describe a framework and a method for estimating public interest
from the implicit negative feedback collected from the IPTV audience. Our
research focuses primarily on the channel change events and their match with
the content information obtained from closed captions. The presented framework
is based on concept modeling, viewership profiling, and combines the implicit
viewer reactions (channel changes) into an interest score. The proposed framework
addresses both above mentioned disadvantages or concerns. It is able to cover a
much broader population, and it can detect even minor variations in user
behavior. We demonstrate our approach on a large pseudonymized real-world IPTV
dataset provided by an ISP, and show how the results correlate with different
trending topics and with parallel classical long-term population surveys.
12. QUERY
EXPANSION WITH ENRICHED USER PROFILES FOR PERSONALIZED SEARCH UTILIZING
FOLKSONOMY DATA
ABSTRACT:
No comments:
Post a Comment