A Human-in-the-loop Segmented Mixed-effects Modeling Method For Analyzing Wearables Data

Wearables are an important source of big data as they provide real-time high-resolution data logs of health indicators of individuals. Higher-order associations between pairs of variables is common in wearables data. Representing higher-order association curves as piece-wise linear segments in a regression model makes them more interpretable. However, existing methods for identifying the change points for segmented modeling either overfit or have low external validity for wearables data containing repeated measures. Therefore, we propose a human-in-the-loop method for segmented modeling of higher-order pairwise associations between variables in wearables data. Our method uses the smooth function estimated by a generalized additive mixed model to allow the analyst to annotate change point estimates for a segmented mixed-effects model, and thereafter employs the Brent's constrained optimization procedure to fine-tuning the manually provided estimates. We validate our method using three real-world wearables datasets. Our method not only outperforms state-of-the-art modeling methods in terms of prediction performance but also provides more interpretable results. Our study contributes to health data science in terms of developing a new method for interpretable modeling of wearables data. Our analysis uncovers interesting insights on higher order associations for health researchers.

Sentimental Spidering

Despite the increased prevalence of sentiment-related information on the Web, there has been limited work on focused crawlers capable of effectively collecting not only topic-relevant but also sentiment-relevant content. In this article, we propose a novel focused crawler that incorporates topic and sentiment information as well as a graph-based tunneling mechanism for enhanced collection of opinion-rich Web content regarding a particular topic. The graph-based sentiment (GBS) crawler uses a text classifier that employs both topic and sentiment categorization modules to assess the relevance of candidate pages. This information is also used to label nodes in web graphs that are employed by the tunneling mechanism to improve collection recall. Experimental results on two test beds revealed that GBS was able to provide better precision and recall than seven comparison crawlers. Moreover, GBS was able to collect a large proportion of the relevant content after traversing far fewer pages than comparison methods. GBS outperformed comparison methods on various categories of Web pages in the test beds, including collection of blogs, Web forums, and social networking Web site content. Further analysis revealed that both the sentiment classification module and graph-based tunneling mechanism played an integral role in the overall effectiveness of the GBS crawler.

Two New Prediction-Driven Approaches to Discrete Choice Prediction

The ability to predict consumer choices is essential in understanding the demand structure of products and services. Typical discrete choice models that are targeted at providing an understanding of the behavioral process leading to choice outcomes are developed around two main assumptions: the existence of a utility function that represents the preferences over a choice set and the relatively simple and interpretable functional form for the utility function with respect to attributes of alternatives and decision makers. These assumptions lead to models that can be easily interpreted to provide insights into the effects of individual variables, such as price and promotion, on consumer choices. However, these restrictive assumptions might impede the ability of such theory-driven models to deliver accurate predictions and forecasts. In this article, we develop novel approaches targeted at providing more accurate choice predictions. Specifically, we propose two prediction-driven approaches: pairwise preference learning using classification techniques and ranking function learning using evolutionary computation. We compare our proposed approaches with a multiclass classification approach, as well as a standard discrete choice model. Our empirical results show that the proposed approaches achieved significantly higher choice prediction accuracy.