Aims: The aim of this study was to estimate the self-reported domestic incidence of acute gastrointestinal illness in the Swedish population irrespective of route of transmission or type of pathogen causing the disease. Previous studies in Sweden have primarily focused on incidence of acute gastrointestinal illness related to consumption of contaminated food and drinking water. Methods: In May 2009, we sent a questionnaire to 4000 randomly selected persons aged 0-85 years, asking about the number of episodes of stomach disease during the last 12 months. To validate the data on symptoms, we compared the study results with anonymous queries submitted to a Swedish medical website. Results: The response rate was 64%. We estimated that a total number of 2744,778 acute gastrointestinal illness episodes (95% confidence intervals 2475,641-3013,915) occurred between 1 May 2008 and 30 April 2009. Comparing the number of reported episodes with web queries indicated that the low number of episodes during the first 6 months was an effect of seasonality rather than recall bias. Further, the result of the recall bias analysis suggested that the survey captured approximately 65% of the true number of episodes among the respondents. Conclusions: The estimated number of Swedish acute gastrointestinal illness cases in this study is about five times higher than previous estimates. This study provides valuable information on the incidence of gastrointestinal symptoms in Sweden, irrespective of route of transmission, indicating a high burden of acute gastrointestinal illness, especially among children, and large societal costs, primarily due to production losses.

Probabilistic topic models have proven to be an extremely versatile class of mixed-membership models for discovering the thematic structure of text collections. There are many possible applications, covering a broad range of areas of study: technology, natural science, social science and the humanities.

In this thesis, a new efficient parallel Markov Chain Monte Carlo inference algorithm is proposed for Bayesian inference in large topic models. The proposed methods scale well with the corpus size and can be used for other probabilistic topic models and other natural language processing applications. The proposed methods are fast, efficient, scalable, and will converge to the true posterior distribution.

In addition, in this thesis a supervised topic model for high-dimensional text classification is also proposed, with emphasis on interpretable document prediction using the horseshoe shrinkage prior in supervised topic models.

Finally, we develop a model and inference algorithm that can model agenda and framing of political speeches over time with a priori defined topics. We apply the approach to analyze the evolution of immigration discourse in the Swedish parliament by combining theory from political science and communication science with a probabilistic topic model.

Generating user interpretable multi-class predictions in data-rich environments with many classes and explanatory covariates is a daunting task. We introduce Diagonal Orthant Latent Dirichlet Allocation (DOLDA), a supervised topic model for multi-class classification that can handle many classes as well as many covariates. To handle many classes we use the recently proposed Diagonal Orthant probit model (Johndrow et al., in: Proceedings of the sixteenth international conference on artificial intelligence and statistics, 2013) together with an efficient Horseshoe prior for variable selection/shrinkage (Carvalho et al. in Biometrika 97:465–480, 2010). We propose a computationally efficient parallel Gibbs sampler for the new model. An important advantage of DOLDA is that learned topics are directly connected to individual classes without the need for a reference class. We evaluate the model’s predictive accuracy and scalability, and demonstrate DOLDA’s advantage in interpreting the generated predictions.

Topic models, and more specifically the class of Latent Dirichlet Allocation (LDA), are widely used for probabilistic modeling of text. MCMC sampling from the posterior distribution is typically performed using a collapsed Gibbs sampler. We propose a parallel sparse partially collapsed Gibbs sampler and compare its speed and efficiency to state-of-the-art samplers for topic models on five well-known text corpora of differing sizes and properties. In particular, we propose and compare two different strategies for sampling the parameter block with latent topic indicators. The experiments show that the increase in statistical inefficiency from only partial collapsing is smaller than commonly assumed, and can be more than compensated by the speedup from parallelization and sparsity on larger corpora. We also prove that the partially collapsed samplers scale well with the size of the corpus. The proposed algorithm is fast, efficient, exact, and can be used in more modeling situations than the ordinary collapsed sampler.

It is often assumed that topic models benefit from the use of a manually curated stopword list. Constructing this list is time-consuming and often subject to user judgments about what kinds of words are important to the model and the application. Although stopword removal clearly affects which word types appear as most probable terms in topics, we argue that this improvement is superficial, and that topic inference benefits little from the practice of removing stopwords beyond very frequent terms. Removing corpus-specific stopwords after model inference is more transparent and produces similar results to removing those words prior to inference.