Queries used to draw data from high-volume, high-velocity social media data streams, such as Twitter, typically require a set of keywords to filter the data. When topics and conversations change rapidly, initial keywords may become outdated and irrelevant, which may result in incomplete data. We propose a novel technique that improves data collection from social media streams in two ways. First, we develop a query expansion method that identifies and adds emergent keywords to the initial query, which makes the data collection a dynamic process that adapts to changes in social conversations. Second, we develop a "predictive query expansion" method that combines keywords from the streams with external data sources, which enables the construction of new queries that effectively capture emergent events that a user may not have anticipated when initiating the data collection stream. We demonstrate the effectiveness of our approach with an analysis of more than 20.5 million Twitter messages related to the 2015 Baltimore protests. We use newspaper archives as an external data source from which we collect keywords to expand the queries built from the primary stream.Reproducibility: https://github.com/FarahAlshanik/QE

Problems in scientific computing, such as distributing large sparse matrix operations, have analogous formulations as hypergraph partitioning problems. A hypergraph is a generalization of a traditional graph wherein “hyperedges” may connect any number of nodes. As a result, hypergraph partitioning is an NP-Hard problem to both solve or approximate. State-of-the-art algorithms that solve this problem follow the multilevel paradigm, which begins by iteratively “coarsening” the input hypergraph to smaller problem instances that share key structural features. Once identifying an approximate problem that is small enough to be solved directly, that solution can be interpolated and refined to the original problem. While this strategy represents an excellent trade off between quality and running time, it is sensitive to coarsening strategy. In this work we propose using graph embeddings of the initial hypergraph in order to ensure that coarsened problem instances retrain key structural features. Our approach prioritizes coarsening within self-similar regions within the input graph, and leads to significantly improved solution quality across a range of considered hypergraphs.Reproducibility:All source code, plots and experimental data are available athttps://sybrandt.com/2019/partition.

Text preprocessing is an essential step in text mining. Removing words that can negatively impact the quality of prediction algorithms or are not informative enough is a crucial storage-saving technique in text indexing and results in improved computational efficiency. Typically, a generic stop word list is applied to a dataset regardless of the domain. However, many common words are different from one domain to another but have no significance within a particular domain. Eliminating domain-specific common words in a corpus reduces the dimensionality of the feature space, and improves the performance of text mining tasks. In this paper, we present a novel mathematical approach for the automatic extraction of domain-specific words called the hyperplane-based approach. This new approach depends on the notion of low dimensional representation of the word in vector space and its distance from hyperplane. The hyperplane-based approach can significantly reduce text dimensionality by eliminating irrelevant features. We compare the hyperplane-based approach with other feature selection methods, namely χ2and mutual information. An experimental study is performed on three different datasets and five classification algorithms, and measure the dimensionality reduction and the increase in the classification performance. Results indicate that the hyperplane-based approach can reduce the dimensionality of the corpus by 90% and outperforms mutual information. The computational time to identify the domain-specific words is significantly lower than mutual information.Reproducibility: code and results can be found at https://github.com/FarahAlshanik/Domain-Specific-Word-List.

The support vector machines (SVM) is one of the most widely used and practical optimization based classification models in machine learning because of its interpretability and flexibility to produce high quality results. However, the big data imposes a certain difficulty to the most sophisticated but relatively slow versions of SVM, namely, the nonlinear SVM. The complexity of nonlinear SVM solvers and the number of elements in the kernel matrix quadratically increases with the number of samples in training data. Therefore, both runtime and memory requirements are negatively affected. Moreover, the parameter fitting has extra kernel parameters to tune, which exacerbate the runtime even further. This paper proposes an adaptive multilevel learning framework for the nonlinear SVM, which addresses these challenges, improves the classification quality across the refinement process, and leverages multi-threaded parallel processing for better performance. The integration of parameter fitting in the hierarchical learning framework and adaptive process to stop unnecessary computation significantly reduce the running time while increase the overall performance. The experimental results demonstrate reduced variance on prediction over validation and test data across levels in the hierarchy, and significant speedup compared to state-of-the-art nonlinear SVM libraries without a decrease in the classification quality. The code is accessible at https://github.com/esadr/amlsvm.

Medical research is risky and expensive. Drug discovery requires researchers to efficiently winnow thousands of potential targets to a small candidate set. However, scientists spend significant time and money long before seeing the intermediate results that ultimately determine this smaller set. Hypothesis generation systems address this challenge by mining the wealth of publicly available scientific information to predict plausible research directions. We present AGATHA, a deep-learning hypothesis generation system that learns a data-driven ranking criteria to recommend new biomedical connections. We massively validate our system with a temporal holdout wherein we predict connections first introduced after 2015 using data published beforehand. We additionally explore biomedical sub-domains, and demonstrate AGATHA's predictive capacity across the twenty most popular relationship types. Furthermore, we perform an ablation study to examine the aspects of our semantic network that most contribute to recommendation quality. Overall, AGATHA achieves best-in-class recommendation quality when compared to other hypothesis generation systems built to predict across all available biomedical literature. Reproducibility: All code, experimental data, and pre-trained models are available online: sybrandt.com/2020/agatha.

Topic modeling, a method for extracting the underlying themes from a collection of documents, is an increasingly important component of the design of intelligent systems enabling the sense-making of highly dynamic and diverse streams of text data related but not limited to scientific discovery. Traditional methods such as Dynamic Topic Modeling (DTM) do not lend themselves well to direct parallelization because of dependencies from one time step to another. In this paper, we introduce and empirically analyze Clustered Latent Dirichlet Allocation (CLDA), a method for extracting dynamic latent topics from a collection of documents. Our approach is based on data decomposition in which the data is partitioned into segments, followed by topic modeling on the individual segments. The resulting local models are then combined into a global solution using clustering. The decomposition and resulting parallelization leads to very fast runtime even on very large datasets. Our approach furthermore provides insight into how the composition of topics changes over time and can also be applied using other data partitioning strategies over any discrete features of the data, such as geographic features or classes of users. In this paper CLDA is applied successfully to seventeen years of NIPS conference papers (2,484 documents and 3,280,697 words), seventeen years of computer science journal abstracts (533,588 documents and 46,446,184 words), and to forty years of the PubMed corpus (4,025,976 documents and 386,847,695 words). On the PubMed corpus, we demonstrate the versatility of CLDA by segmenting the data by both time and by journal. Our runtime on this corpus demonstrates an ability to function on very large scale datasets.

It is quite evident that majority of the population lives in urban area today than in any time of the human history. This trend seems to increase in coming years. A study [5] says that nearly 80.7% of total population in USA stays in urban area. By 2030 nearly 60% of the population in the world will live in or move to cities. With the increase in urban population, it is important to keep an eye on criminal activities. By doing so, governments can enforce intelligent policing systems and hence many government agencies and local authorities have made the crime data publicly available. In this paper, we analyze Chicago city crime data fused with other social information sources using network analytic techniques to predict criminal activity for the next year. We observe that as we add more layers of data which represent different aspects of the society, the quality of prediction is improved. Our prediction models not just predict total number of crimes for the whole Chicago city, rather they predict number of crimes for all types of crimes and for different regions in City of Chicago.

The potential for automatic hypothesis generation (HG) systems to improve research productivity keeps pace with the growing set of publicly available scientific information. But as data becomes easier to acquire, we must understand the effect different textual data sources have on our resulting hypotheses. Are abstracts enough for HG, or does it need full-text papers? How many papers does an HG system need to make valuable predictions? How sensitive is a general-purpose HG system to hyperparameter values or input quality? What effect does corpus size and document length have on HG results? To answer these questions we train multiple versions of knowledge network-based HG system, MOLIERE, on varying corpora in order to compare challenges and trade offs in terms of result quality and computational requirements. MOLIERE generalizes main principles of similar knowledge network-based HG systems and reinforces them with topic modeling components. The corpora include the abstract and full-text versions of PubMed Central, as well as iterative halves of MEDLINE, which allows us to compare the effect document length and count has on the results. We find that, quantitatively, corpora with a higher median document length result in marginally higher quality results, yet require substantially longer to process. However, qualitatively, full-length papers introduce a significant number of intruder terms to the resulting topics, which decreases human interpretability. Additionally, we find that the effect of document length is greater than that of document count, even if both sets contain only paper abstracts.Reproducibility: Our code and data are available online at sybrandt.com/2018/abstracts.

The first step of many research projects is to define and rank a short list of candidates for study. In the modern rapidity of scientific progress, some turn to automated hypothesis generation (HG) systems to aid this process. These systems can identify implicit or overlooked connections within a large scientific corpus, and while their importance grows alongside the pace of science, they lack thorough validation. Without any standard numerical evaluation method, many validate general-purpose HG systems by rediscovering a handful of historical findings, and some wishing to be more thorough may run laboratory experiments based on automatic suggestions. These methods are expensive, time consuming, and cannot scale. Thus, we present a numerical evaluation framework for the purpose of validating HG systems that leverages thousands of validation hypotheses. This method evaluates a HG system by its ability to rank hypotheses by plausibility; a process reminiscent of human candidate selection. Because HG systems do not produce a ranking criteria, specifically those that produce topic models, we additionally present novel metrics to quantify the plausibility of hypotheses given topic model system output. Finally, we demonstrate that our proposed validation method aligns with real-world research goals by deploying our method within MOLIERE, our recent topic-driven HG system, in order to automatically generate a set of candidate genes related to HIV-associated neurodegenerative disease (HAND). By performing laboratory experiments based on this candidate set, we discover a new connection between HAND and Dead Box RNA Helicase 3 (DDX3). Reproducibility: code, validation data, and results can be found at sybrandt.com/2018/validation.

Methods for detecting and summarizing emergent keywords have been extensively studied since social media and microblogging activities have started to play an important role in data analysis and decision making. We present a fast system for monitoring emergent keywords and summarizing a document stream based on the dynamic semantic graphs of streaming documents. We introduce the notion of dynamic eigenvector centrality for ranking emergent keywords, and present an algorithm for summarizing emergent events that is based on the minimum weight set cover. Our system is demonstrated on the streaming Twitter data related to public security.

Hypothesis generation is becoming a crucial time-saving technique which allows biomedical researchers to quickly discover implicit connections between important concepts. Typically, these systems operate on domain-specific fractions of public medical data. MOLIERE, in contrast, utilizes information from over 24.5 million documents. At the heart of our approach lies a multi-modal and multi-relational network of biomedical objects extracted from several heterogeneous datasets from the National Center for Biotechnology Information (NCBI). These objects include but are not limited to scientific papers, keywords, genes, proteins, diseases, and diagnoses. We model hypotheses using Latent Dirichlet Allocation applied on abstracts found near shortest paths discovered within this network, and demonstrate the effectiveness of MOLIERE by performing hypothesis generation on historical data. Our network, implementation, and resulting data are all publicly available for the broad scientific community.