Information Interaction Profile of Choice Adoption

Interactions between pieces of information (entities) play a substantial role in the way an individual acts on them: adoption of a product, the spread of news, strategy choice, etc. However, the underlying interaction mechanisms are often unknown and have been little explored in the literature. We introduce an efficient method to infer both the entities interaction network and its evolution according to the temporal distance separating interacting entities; together, they form the interaction profile. The interaction profile allows characterizing the mechanisms of the interaction processes. We approach this problem via a convex model based on recent advances in multi-kernel inference. We consider an ordered sequence of exposures to entities (URL, ads, situations) and the actions the user exerts on them (share, click, decision). We study how users exhibit different behaviors according to combinations of exposures they have been exposed to. We show that the effect of a combination of exposures on a user is more than the sum of each exposure's independent effect--there is an interaction. We reduce this modeling to a non-parametric convex optimization problem that can be solved in parallel. Our method recovers state-of-the-art results on interaction processes on three real-world datasets and outperforms baselines in the inference of the underlying data generation mechanisms. Finally, we show that interaction profiles can be visualized intuitively, easing the interpretation of the model.

Powered Dirichlet Process for Controlling the Importance of "Rich-Get-Richer" Prior Assumptions in Bayesian Clustering

One of the most used priors in Bayesian clustering is the Dirichlet prior. It can be expressed as a Chinese Restaurant Process. This process allows nonparametric estimation of the number of clusters when partitioning datasets. Its key feature is the "rich-get-richer" property, which assumes a cluster has an a priori probability to get chosen linearly dependent on population. In this paper, we show that such prior is not always the best choice to model data. We derive the Powered Chinese Restaurant process from a modified version of the Dirichlet-Multinomial distribution to answer this problem. We then develop some of its fundamental properties (expected number of clusters, convergence). Unlike state-of-the-art efforts in this direction, this new formulation allows for direct control of the importance of the "rich-get-richer" prior.

Interactions in information spread: quantification and interpretation using stochastic block models

In most real-world applications, it is seldom the case that a given observable evolves independently of its environment. In social networks, users' behavior results from the people they interact with, news in their feed, or trending topics. In natural language, the meaning of phrases emerges from the combination of words. In general medicine, a diagnosis is established on the basis of the interaction of symptoms. Here, we propose a new model, the Interactive Mixed Membership Stochastic Block Model (IMMSBM), which investigates the role of interactions between entities (hashtags, words, memes, etc.) and quantifies their importance within the aforementioned corpora. We find that interactions play an important role in those corpora. In inference tasks, taking them into account leads to average relative changes with respect to non-interactive models of up to 150\% in the probability of an outcome. Furthermore, their role greatly improves the predictive power of the model. Our findings suggest that neglecting interactions when modeling real-world phenomena might lead to incorrect conclusions being drawn.

Document Network Projection in Pretrained Word Embedding Space

We present Regularized Linear Embedding (RLE), a novel method that projects a collection of linked documents (e.g. citation network) into a pretrained word embedding space. In addition to the textual content, we leverage a matrix of pairwise similarities providing complementary information (e.g., the network proximity of two documents in a citation graph). We first build a simple word vector average for each document, and we use the similarities to alter this average representation. The document representations can help to solve many information retrieval tasks, such as recommendation, classification and clustering. We demonstrate that our approach outperforms or matches existing document network embedding methods on node classification and link prediction tasks. Furthermore, we show that it helps identifying relevant keywords to describe document classes.

Inductive Document Network Embedding with Topic-Word Attention

Document network embedding aims at learning representations for a structured text corpus i.e. when documents are linked to each other. Recent algorithms extend network embedding approaches by incorporating the text content associated with the nodes in their formulations. In most cases, it is hard to interpret the learned representations. Moreover, little importance is given to the generalization to new documents that are not observed within the network. In this paper, we propose an interpretable and inductive document network embedding method. We introduce a novel mechanism, the Topic-Word Attention (TWA), that generates document representations based on the interplay between word and topic representations. We train these word and topic vectors through our general model, Inductive Document Network Embedding (IDNE), by leveraging the connections in the document network. Quantitative evaluations show that our approach achieves state-of-the-art performance on various networks and we qualitatively show that our model produces meaningful and interpretable representations of the words, topics and documents.

How to detect novelty in textual data streams? A comparative study of existing methods

Since datasets with annotation for novelty at the document and/or word level are not easily available, we present a simulation framework that allows us to create different textual datasets in which we control the way novelty occurs. We also present a benchmark of existing methods for novelty detection in textual data streams. We define a few tasks to solve and compare several state-of-the-art methods. The simulation framework allows us to evaluate their performances according to a set of limited scenarios and test their sensitivity to some parameters. Finally, we experiment with the same methods on different kinds of novelty in the New York Times Annotated Dataset.

Link Prediction with Mutual Attention for Text-Attributed Networks

In this extended abstract, we present an algorithm that learns a similarity measure between documents from the network topology of a structured corpus. We leverage the Scaled Dot-Product Attention, a recently proposed attention mechanism, to design a mutual attention mechanism between pairs of documents. To train its parameters, we use the network links as supervision. We provide preliminary experiment results with a citation dataset on two prediction tasks, demonstrating the capacity of our model to learn a meaningful textual similarity.

Global Vectors for Node Representations

Most network embedding algorithms consist in measuring co-occurrences of nodes via random walks then learning the embeddings using Skip-Gram with Negative Sampling. While it has proven to be a relevant choice, there are alternatives, such as GloVe, which has not been investigated yet for network embedding. Even though SGNS better handles non co-occurrence than GloVe, it has a worse time-complexity. In this paper, we propose a matrix factorization approach for network embedding, inspired by GloVe, that better handles non co-occurrence with a competitive time-complexity. We also show how to extend this model to deal with networks where nodes are documents, by simultaneously learning word, node and document representations. Quantitative evaluations show that our model achieves state-of-the-art performance, while not being so sensitive to the choice of hyper-parameters. Qualitatively speaking, we show how our model helps exploring a network of documents by generating complementary network-oriented and content-oriented keywords.

Non-parametric clustering over user features and latent behavioral functions with dual-view mixture models

We present a dual-view mixture model to cluster users based on their features and latent behavioral functions. Every component of the mixture model represents a probability density over a feature view for observed user attributes and a behavior view for latent behavioral functions that are indirectly observed through user actions or behaviors. Our task is to infer the groups of users as well as their latent behavioral functions. We also propose a non-parametric version based on a Dirichlet Process to automatically infer the number of clusters. We test the properties and performance of the model on a synthetic dataset that represents the participation of users in the threads of an online forum. Experiments show that dual-view models outperform single-view ones when one of the views lacks information.

Automatic Language Identification for Romance Languages using Stop Words and Diacritics

Automatic language identification is a natural language processing problem that tries to determine the natural language of a given content. In this paper we present a statistical method for automatic language identification of written text using dictionaries containing stop words and diacritics. We propose different approaches that combine the two dictionaries to accurately determine the language of textual corpora. This method was chosen because stop words and diacritics are very specific to a language, although some languages have some similar words and special characters they are not all common. The languages taken into account were romance languages because they are very similar and usually it is hard to distinguish between them from a computational point of view. We have tested our method using a Twitter corpus and a news article corpus. Both corpora consists of UTF-8 encoded text, so the diacritics could be taken into account, in the case that the text has no diacritics only the stop words are used to determine the language of the text. The experimental results show that the proposed method has an accuracy of over 90% for small texts and over 99.8% for