Online social networks like Twitter and Facebook produce an overwhelming amount of information every day. However, research suggests that much of this content focuses on a reasonably sized set of ongoing events or topics that are both temporally and geographically situated. These patterns are especially observable when the data that is generated contains geospatial information, usually generated by a location enabled device such as a smartphone. In this paper, we consider a data set of 1.4 million geo-tagged tweets from a country during a large social movement, where social events and demonstrations occurred frequently. We use a probabilistic graphical model to discover these events within the data in a way that informs us of their spatial, temporal and topical focus. Quantitative analysis suggests that the streaming algorithm proposed in the paper uncovers both well-known events and lesser-known but important events that occurred within the timeframe of the dataset. In addition, the model can be used to predict the location and time of texts that do not have these pieces of information, which accounts for the much of the data on the web.

Given the rapid growth of social media websites and the ease of aggregating ever-richer social data, an inevitable research question that can be expected to emerge is whether different interaction patterns of individuals and their meaningful interpretation can be captured for social network analysis. In this work, we present a novel solution that discovers occurrences of prototypical 'ego network' patterns from social media and mobile-phone networks, to provide a data-driven instrument to be used in behavioral sciences for graph interpretations. We analyze nine datasets gathered from social media websites and mobile phones, together with 13 network measures, and three unsupervised clustering algorithms. Further, we use an unsupervised feature similarity technique to reduce redundancy and extract compact features from the data. The reduced feature subsets are then used to discover ego patterns using various clustering techniques. By cluster analysis, we discover that eight distinct ego neighborhood patterns or ego graphs have emerged. This categorization allows concise analysis of users' data as they change over time. We provide fine-grained analysis for the validity and quality of clustering results. We perform clustering verification based on the following three intuitions: i) analyzing the clustering patterns for the same set of users crawled from three social media networks, ii) associating metadata information with the clusters and evaluating their performance on real networks, iii) studying selected participants over an extended period to analyze their behavior.

Students in a Massive Open Online Course (MOOC) interact with each other and the course staff through online discussion forums. While discussion forums play a central role in MOOCs, they also pose a challenge for instructors. The large number of student posts makes it difficult for an instructor to know where to intervene to answer questions, resolve issues, and provide feedback. In this work, we focus on automatically predicting speech acts in MOOC forum posts. Our speech act categories describe the purpose or function of the post in the ongoing discussion. Specifically, we address three main research questions. First, we investigate whether crowdsourced workers can reliably label MOOC forum posts using our speech act definitions. Second, we investigate whether our speech acts can help predict instructor interventions and assignment completion and performance. Finally, we investigate which types of features (derived from the post content, author, and surrounding context) are most effective for predicting our different speech act categories.

We consider the classic problem of establishing a statistical ranking of a set of n items given a set of inconsistent and incomplete pairwise comparisons between such items. Instantiations of this problem occur in numerous applications in data analysis (e.g., ranking teams in sports data), computer vision, and machine learning. We formulate the above problem of ranking with incomplete noisy information as an instance of the group synchronization problem over the group SO(2) of planar rotations, whose usefulness has been demonstrated in numerous applications in recent years. Its least squares solution can be approximated by either a spectral or a semidefinite programming (SDP) relaxation, followed by a rounding procedure. We perform extensive numerical simulations on both synthetic and real-world data sets, showing that our proposed method compares favorably to other algorithms from the recent literature. Existing theoretical guarantees on the group synchronization problem imply lower bounds on the largest amount of noise permissible in the ranking data while still achieving exact recovery. We propose a similar synchronization-based algorithm for the rank-aggregation problem, which integrates in a globally consistent ranking pairwise comparisons given by different rating systems on the same set of items. We also discuss the problem of semi-supervised ranking when there is available information on the ground truth rank of a subset of players, and propose an algorithm based on SDP which recovers the ranks of the remaining players. Finally, synchronization-based ranking, combined with a spectral technique for the densest subgraph problem, allows one to extract locally-consistent partial rankings, in other words, to identify the rank of a small subset of players whose pairwise comparisons are less noisy than the rest of the data, which other methods are not able to identify.

ABSTRACT Learned feature representations and sub-phoneme posteriors from Deep Neural Networks (DNNs) have been used separately to produce significant performance gains for speaker and language recognition tasks. In this work we show how these gains are possible using a single DNN for both speaker and language recognition. The unified DNN approach is shown to yield substantial performance improvements on the the 2013 Domain Adaptation Challenge speaker recognition task (55% reduction in EER for the out-of-domain condition) and on the NIST 2011 Language Recognition Evaluation (48% reduction in EER for the 30s test condition). Index Terms: i-vector, DNN, bottleneck features, speaker recognition, language recognition 1. INTRODUCTION The impressive gains in performance obtained using deep neural networks (DNNs) for automatic speech recognition (ASR) [1] have motivated the application of DNNs to other speech technologies such as speaker recognition (SR) and language recognition (LR) [2, 3, 4, 5, 6, 7, 8, 9]. Two general methods of applying DNN's to the SR and LR tasks have been shown to be effective.

Over the last decade there has been increasing concern about the biases embodied in traditional evaluation methods for Natural Language Processing/Learning, particularly methods borrowed from Information Retrieval. Without knowledge of the Bias and Prevalence of the contingency being tested, or equivalently the expectation due to chance, the simple conditional probabilities Recall, Precision and Accuracy are not meaningful as evaluation measures, either individually or in combinations such as F-factor. The existence of bias in NLP measures leads to the 'improvement' of systems by increasing their bias, such as the practice of improving tagging and parsing scores by using most common value (e.g. water is always a Noun) rather than the attempting to discover the correct one. The measures Cohen Kappa and Powers Informedness are discussed as unbiased alternative to Recall and related to the psychologically significant measure DeltaP. In this paper we will analyze both biased and unbiased measures theoretically, characterizing the precise relationship between all these measures as well as evaluating the evaluation measures themselves empirically using a Monte Carlo simulation.

The article derives a novel Gram-Charlier A (GCA) Series based Extended Rule-of-Thumb (ExROT) for bandwidth selection in Kernel Density Estimation (KDE). There are existing various bandwidth selection rules achieving minimization of the Asymptotic Mean Integrated Square Error (AMISE) between the estimated probability density function (PDF) and the actual PDF. The rules differ in a way to estimate the integration of the squared second order derivative of an unknown PDF $(f(\cdot))$, identified as the roughness $R(f''(\cdot))$. The simplest Rule-of-Thumb (ROT) estimates $R(f''(\cdot))$ with an assumption that the density being estimated is Gaussian. Intuitively, better estimation of $R(f''(\cdot))$ and consequently better bandwidth selection rules can be derived, if the unknown PDF is approximated through an infinite series expansion based on a more generalized density assumption. As a demonstration and verification to this concept, the ExROT derived in the article uses an extended assumption that the density being estimated is near Gaussian. This helps use of the GCA expansion as an approximation to the unknown near Gaussian PDF. The ExROT for univariate KDE is extended to that for multivariate KDE. The required multivariate AMISE criteria is re-derived using elementary calculus of several variables, instead of Tensor calculus. The derivation uses the Kronecker product and the vector differential operator to achieve the AMISE expression in vector notations. There is also derived ExROT for kernel based density derivative estimator.

We propose a novel parameterized family of Mixed Membership Mallows Models (M4) to account for variability in pairwise comparisons generated by a heterogeneous population of noisy and inconsistent users. M4 models individual preferences as a user-specific probabilistic mixture of shared latent Mallows components. Our key algorithmic insight for estimation is to establish a statistical connection between M4 and topic models by viewing pairwise comparisons as words, and users as documents. This key insight leads us to explore Mallows components with a separable structure and leverage recent advances in separable topic discovery. While separability appears to be overly restrictive, we nevertheless show that it is an inevitable outcome of a relatively small number of latent Mallows components in a world of large number of items. We then develop an algorithm based on robust extreme-point identification of convex polygons to learn the reference rankings, and is provably consistent with polynomial sample complexity guarantees. We demonstrate that our new model is empirically competitive with the current state-of-the-art approaches in predicting real-world preferences.

We establish bounds on the KL divergence between two multivariate Gaussian distributions in terms of the Hamming distance between the edge sets of the corresponding graphical models. We show that the KL divergence is bounded below by a constant when the graphs differ by at least one edge; this is essentially the tightest possible bound, since classes of graphs exist for which the edge discrepancy increases but the KL divergence remains bounded above by a constant. As a natural corollary to our KL lower bound, we also establish a sample size requirement for correct model selection via maximum likelihood estimation. Our results rigorize the notion that it is essential to estimate the edge structure of a Gaussian graphical model accurately in order to approximate the true distribution to close precision.

We define the beta diffusion tree, a random tree structure with a set of leaves that defines a collection of overlapping subsets of objects, known as a feature allocation. A generative process for the tree structure is defined in terms of particles (representing the objects) diffusing in some continuous space, analogously to the Dirichlet diffusion tree (Neal, 2003b), which defines a tree structure over partitions (i.e., non-overlapping subsets) of the objects. Unlike in the Dirichlet diffusion tree, multiple copies of a particle may exist and diffuse along multiple branches in the beta diffusion tree, and an object may therefore belong to multiple subsets of particles. We demonstrate how to build a hierarchically-clustered factor analysis model with the beta diffusion tree and how to perform inference over the random tree structures with a Markov chain Monte Carlo algorithm. We conclude with several numerical experiments on missing data problems with data sets of gene expression microarrays, international development statistics, and intranational socioeconomic measurements.