Online enterprise communities often have clear informational goals, e.g. for experts to answer novices’ factual questions. However, emotional support is also critical for developing online social relationships. But what is the optimal balance between informational and emotional communication for such communities? To address this, we develop and validate a model to assess the relative prevalence...

The present article explores how factual and fictional media portrayals may activate culturally shared racial and gender stereotypes and influence subsequent judgments involving members of stereotyped groups. In line with previous research (Power, Murphy, and Coover 1996), new data are presented that demonstrate that exposure to a stereotypic or counterstereotypic portrayal primes consistent in...

Abstractive summarization is the process of generating a summary given document as input. Although significant progress has been made, factual inconsistency between and generated still limits its practical applications. Previous work found that probabilities assigned by generation model reflect preferences for summary, including preference consistency, language or knowledge prior well. To separ...

In “Any Good News in Soft News?” Markus Prior investigates whether, beyond enhancing their attentiveness to select political issues (Baum, 2002a), consumers also learn about politics from soft news. He presents evidence suggesting that the audience for soft news is much smaller than that for hard news, and that a self-expressed preference for soft news outlets is associated with at most sporadi...

This paper describes methods to examine factual, natural language sentences in order to generate factual, natural language questions whose answers are found in the sentences. These methods rely on rules that look for patterns in the syntactic structure, named entities, and grammatical relations of a sentence. The extraction of these pieces of information from a sentence is not the focus of this...

To create more powerful knowledge acquisition systems, we not only need better acquisition tools, but we need to change the architecture of the knowledge based systems we create so that their structure will provide better support for acquisition. Current acquisition tools permit users to modify factual knowledge but they provide limited support for modifying problem solving knowledge. In this p...