We present ProxiModel, a novel event mining framework for extracting high-quality structured event knowledge from large, redundant, and noisy news data sources. The proposed model differentiates itself from other approaches by modeling both the event correlation within each individual document as well as across the corpus. To facilitate this, we introduce the concept of a proximity-network, a novel space-efficient data structure to facilitate scalable event mining. This proximity network captures the corpus-level co-occurence statistics for candidate event descriptors, event attributes, as well as their connections. We probabilistically model the proximity network as a generative process with sparsity-inducing regularization. This allows us to efficiently and effectively extract high-quality and interpretable news events. Experiments on three different news corpora demonstrate that the proposed method is effective and robust at generating high-quality event descriptors and attributes. We briefly detail many interesting applications from our proposed framework such as news summarization, event tracking and multi-dimensional analysis on news. Finally, we explore a case study on visualizing the events for a Japan Tsunami news corpus and demonstrate ProxiModel's ability to automatically summarize emerging news events.

Document representation is a fundamental problem for text mining. Many efforts have been done to generate concise yet semantic representation, such as bag-of-words, phrase, sentence and topic-level descriptions. Nevertheless, most existing techniques counter difficulties in handling monolingual comparable corpus, which is a collection of monolingual documents conveying the same topic. In this paper, we propose the use of frame, a high-level semantic unit, and construct frame-based representations to semantically describe documents by bags of frames, using an information network approach. One major challenge in this representation is that semantically similar frames may be of different forms. For example, "radiation leaked" in one news article can appear as "the level of radiation increased" in another article. To tackle the problem, a text-based information network is constructed among frames and words, and a link-based similarity measure called SynRank is proposed to calculate similarity between frames. As a result, different variations of the semantically similar frames are merged into a single descriptive frame using clustering, and a document can then be represented as a bag of representative frames. It turns out that frame-based document representation not only is more interpretable, but also can facilitate other text analysis tasks such as event tracking effectively. We conduct both qualitative and quantitative experiments on three comparable news corpora, to study the effectiveness of frame-based document representation and the similarity measure SynRank, respectively, and demonstrate that the superior performance of frame-based document representation on different real-world applications.

Topic models, which factor each document into different topics and represent each topic as a distribution of terms, have been widely and successfully used to better understand collections of text documents. However, documents are also associated with further information, such as the set of real-world entities mentioned in them. For example, news articles are usually related to several people, organizations, countries or locations. Since those associated entities carry rich information, it is highly desirable to build more expressive, entity-based topic models, which can capture the term distributions for each topic, each entity, as well as each topic-entity pair. In this paper, we therefore introduce a novel Entity Topic Model (ETM) for documents that are associated with a set of entities. ETM not only models the generative process of a term given its topic and entity information, but also models the correlation of entity term distributions and topic term distributions. A Gibbs sampling-based algorithm is proposed to learn the model. Experiments on real datasets demonstrate the effectiveness of our approach over several state-of-the-art baselines.

Pattern mining is a fundamental problem that has a wide range of applications. In this paper, we study the problem of finding a minimum set of signature patterns that explain all data. In the problem, we are given objects where each object has an item set and a label. A pattern is called a signature pattern if all objects with the pattern have the same label. This problem has many interesting applications such as assertion mining in hardware design and identifying failure causes from various log data. We show that the previous pattern mining methods are not suitable for mining signature patterns and identify the problems. Then we propose a novel pattern enumeration method which we call Pattern Shrink. Our method is strongly coupled with another novel method that is very similar to finding a local optimum with a negligible loss in performance. Our proposed methods show a speedup of more than ten times over the previous methods. Our methods are flexible enough to be extended to mining high confidence patterns, instead of signature patterns.

Fear of increasing prices and concern about climate change are motivating residential power conservation efforts. We investigate the effectiveness of several unsupervised disaggregation methods on low frequency power measurements collected in real homes. Specifically, we consider variants of the factorial hidden Markov model. Our results indicate that a conditional factorial hidden semi-Markov model, which integrates additional features related to when and how appliances are used in the home and more accurately represents the power use of individual appliances, outperforms the other unsupervised disaggregation methods. Our results show that unsupervised techniques can provide perappliance power usage information in a non-invasive manner, which is ideal for enabling power conservation efforts.

In the past, there have been dozens of studies on automatic authorship classification, and many of these studies concluded that the writing style is one of the best indicators for original authorship. From among the hundreds of features which were developed, syntactic features were best able to reflect an author's writing style. However, due to the high computational complexity for extracting and computing syntactic features, only simple variations of basic syntactic features such as function words, POS(Part of Speech) tags, and rewrite rules were considered. In this paper, we propose a new feature set of k-embedded-edge subtree patterns that holds more syntactic information than previous feature sets. We also propose a novel approach to directly mining them from a given set of syntactic trees. We show that this approach reduces the computational burden of using complex syntactic structures as the feature set. Comprehensive experiments on real-world datasets demonstrate that our approach is reliable and more accurate than previous studies.

WINACS (Web-based Information Network Analysis for Computer Science) is a project that incorporates many recent, exciting developments in data sciences to construct a Web-based computer science information network and to discover, retrieve, rank, cluster, and analyze such an information network. With the rapid development of the Web, huge amounts of information are available in the form of Web documents, structures, and links. It has been a dream of the database and Web communities to harvest such information and reconcile the unstructured nature of the Web with the neat, semi-structured schemas of the database paradigm. Taking computer science as a dedicated domain, WINACS first discovers related Web entity structures, and then constructs a heterogeneous computer science information network in order to rank, cluster and analyze this network and support intelligent and analytical queries.