Analysis of Statistical Question Classification for Fact-Based Questions

Question classification systems play an important role in question answering systems and can be used in a wide range of other domains. The goal of question classification is to accurately assign labels to questions based on expected answer type. Most approaches in the past have relied on matching questions against hand-crafted rules. However, rules require laborious effort to create and often suffer from being too specific. Statistical question classification methods overcome these issues by employing machine learning techniques. We empirically show that a statistical approach is robust and achieves good performance on three diverse data sets with little or no hand tuning. Furthermore, we examine the role different syntactic and semantic features have on performance. We find that semantic features tend to increase performance more than purely syntactic features. Finally, we analyze common causes of misclassification error and provide insight into ways they may be overcome.     

Disciplined freedom,branded authenticity,and dependable independence: how tensions enact flexibility in lifestyle blogging careers

Analyzing 219 blog posts from 52 self-employed women lifestyle bloggers in North America, this study shows how these digital professionals navigate tensions and communicatively constitute work flexibility. In their narratives, women bloggers employed tension management approaches such as reframing, continual connections, and reflective practice in response to tensions in enacting temporal–spatial, identity, and financial flexibility. Specifically, women followed oxymoronic constructions – disciplined freedom, branded authenticity, and dependable independence – to embrace and transform competing poles of fluidity?structure, authenticity?marketability, and independence?interconnection. Expanding work–life research to the self-employed digital labor context, this study responds to recent calls to uncover more-than tension management strategies in empirical settings and contributes to a tension-centered, contextual, and processual analysis of workplace flexibility construction.     

Relational turbulence and perceptions of partner support during reintegration after military deployment

The transition from deployment to reintegration can be stressful for returning military personnel and at-home partners, and support plays a key role in their ability to transition effectively. We draw on relational turbulence theory to advance predictions about how parameters of the relationship between returning service members and at-home partners predict their perceptions of their partner’s support during the post-deployment transition. We surveyed 235 individuals (117 returning service members, 118 at-home partners) who had experienced the transition within the past 6 months. Findings consistent with the theory indicated that relational turbulence partially mediated the negative associations that relational uncertainty and interference from a partner shared with partner support. Partner uncertainty was a direct negative predictor of partner support as well. We consider how these results extend theory, research, and practice.     

Institutional policy process improvement: using structurating activity theory to inform practice

Organizational communication scholars are increasingly called upon to use theoretical knowledge to address problematic processes in public institutions. This article reports a process improvement project focused on a university conflict of interest (COI) policy as an example of how scholars can engage theory to improve ongoing policy processes. The project team included communication scholars and research administration staff who designed, implemented, and evaluated the mixed-methods project guided by structurating activity theory. Baseline survey results were used to design the process improvement project. Results of the follow-up survey indicate that researchers who participated in some aspect of the process improvement project (i.e. attending a policy café, using the redesigned website, or reading the new Quick Reference Guide) reported higher levels of policy communication and knowledge and more positive attitudes toward the COI policy than researchers who had not engaged with process improvement efforts. We offer theoretical and practical implications of results for organizational communication scholars and practitioners.