Search

A long line of literature has focused on the problem of selecting a team of individuals from a large pool of candidates, such that certain constraints are respected, and a given objective function is maximized. Even though extant research has successfully considered diverse families of objective functions and constraints, one of the most common limitations is the focus on the single-team paradigm. Despite its well-documented applications in multiple domains, this paradigm is not appropriate when the team-builder needs to partition the entire population into multiple teams. Team-partitioning tasks are very common in an educational setting, in which the teacher has to partition the students in her class into teams for collaborative projects. The task also emerges in the context of organizations, when managers need to partition the workforce into teams with specific properties to tackle relevant projects. In this work, we extend the team formation literature by introducing the Guided Team-Partitioning (GTP) problem, which asks for the partitioning of a population into teams such that the centroid of each team is as close as possible to a given target vector. As we describe in detail in our work, this formulation allows the team-builder to control the composition of the produced teams and has natural applications in practical settings. Algorithms for the GTP need to simultaneously consider the composition of multiple non-overlapping teams that compete for the same population of candidates. This makes the problem considerably more challenging than formulations that focus on the optimization of a single team. In fact, we prove that GTP is NP-hard to solve and even to approximate. The complexity of the problem motivates us to consider efficient algorithmic heuristics, which we evaluate via experiments on both real and synthetic datasets.

In recent years, the proliferation of online resumes and the need to evaluate large populations of candidates for on-site and virtual teams have led to a growing interest in automated team-formation. Given a large pool of candidates, the general problem requires the selection of a team of experts to complete a given task. Surprisingly, while ongoing research has studied numerous variations with different constraints, it has overlooked a factor with a well-documented impact on team cohesion and performance: team faultlines. Addressing this gap is challenging, as the available measures for faultlines in existing teams cannot be efficiently applied to faultline optimization. In this work, we meet this challenge with a new measure that can be efficiently used for both faultline measurement and minimization. We then use the measure to solve the problem of automatically partitioning a large population into low-faultline teams. By introducing faultlines to the team-formation literature, our work creates exciting opportunities for algorithmic work on faultline optimization, as well as on work that combines and studies the connection of faultlines with other influential team characteristics.

The proliferation of mobile handheld devices in combination with the technological advancements in mobile computing has led to a number of innovative services that make use of the location information available on such devices. Traditional yellow pages websites have now moved to mobile platforms, giving the opportunity to local businesses and potential, near-by, customers to connect. These platforms can offer an affordable advertisement channel to local businesses. One of the mechanisms offered by location-based social networks (LBSNs) allows businesses to provide special offers to their customers that connect through the platform. We collect a large time-series dataset from approximately 14 million venues on Foursquare and analyze the performance of such campaigns using randomization techniques and (non-parametric) hypothesis testing with statistical bootstrapping. Our main finding indicates that this type of promotions are not as effective as anecdote success stories might suggest. Finally, we design classifiers by extracting three different types of features that are able to provide an educated decision on whether a special offer campaign for a local business will succeed or not both in short and long term., Comment: in The 9th International AAAI Conference on Web and Social Media (ICWSM 2015)

Thousands of documents are made available to the users via the web on a daily basis. One of the most extensively studied problems in the context of such document streams is burst identification. Given a term t, a burst is generally exhibited when an unusually high frequency is observed for t. While spatial and temporal burstiness have been studied individually in the past, our work is the first to simultaneously track and measure spatiotemporal term burstiness. In addition, we use the mined burstiness information toward an efficient document-search engine: given a user's query of terms, our engine returns a ranked list of documents discussing influential events with a strong spatiotemporal impact. We demonstrate the efficiency of our methods with an extensive experimental evaluation on real and synthetic datasets., Comment: VLDB2012

The evolution of the Internet during the last years, has lead to a dramatic increase of the size of its graph at the Autonomous System (AS) level. Soon - if not already - its size will make the latter impractical for use from the research community, e.g. for protocol testing. Reproducing a smaller size, snapshot of the AS graph is thus important. However, the first step towards this direction is to obtain the ability to faithfully reproduce the full AS topology. The objective of our work, is to create a generator able to accurately emulate and reproduce the distinctive properties of the Internet graph. Our approach is based on (a) the identification of the jellyfish-like structure [1] of the Internet and (b) the consideration of the peer-to-peer and customer-provider relations between ASs. We are the first to exploit the distinctive structure of the Internet graph together with utilizing the information provided by the AS relationships in order to create a tool with the aforementioned capabilities. Comparing our generator with the existing ones in the literature, the main difference is found on the fact that our tool does not try to satisfy specific metrics, but tries to remain faithful to the conceptual model of the Internet structure. In addition, our approach can lead to (i) the identification of important attributes and patterns in the Internet AS topology, as well as, (ii) the extraction of valuable information on the various relationships between ASs and their effect on the formulation of the Internet structure. We implement our graph generator and we evaluate it using the largest and most recent available dataset for the AS topology. Our evaluations, clearly show the ability of our tool to capture the structural properties of the Internet topology at the AS level with high accuracy., Comment: 9 pages