DePaul University

About: DePaul University is a education organization based out in Chicago, Illinois, United States. It is known for research contribution in the topics: Population & Poison control. The organization has 5658 authors who have published 11562 publications receiving 295257 citations.

Controlling Popularity Bias in Learning-to-Rank Recommendation

Abstract: Many recommendation algorithms suffer from popularity bias in their output: popular items are recommended frequently and less popular ones rarely, if at all. However, less popular, long-tail items are precisely those that are often desirable recommendations. In this paper, we introduce a flexible regularization-based framework to enhance the long-tail coverage of recommendation lists in a learning-to-rank algorithm. We show that regularization provides a tunable mechanism for controlling the trade-off between accuracy and coverage. Moreover, the experimental results using two data sets show that it is possible to improve coverage of long tail items without substantial loss of ranking performance.

A Model of Social Entrepreneurial Discovery

Abstract: Social entrepreneurship activity continues to surge tremendously in market and economic systems around the world. Yet, social entrepreneurship theory and understanding lag far behind its practice. For instance, the nature of the entrepreneurial discovery phenomenon, a critical area of inquiry in general entrepreneurship theory, receives no attention in the specific context of social entrepreneurship. To address the gap, we conceptualize social entrepreneurial discovery based on an extension of corporate social responsibility into social entrepreneurship contexts. We develop a model that emphasizes mobilization and timing as underpinnings of social entrepreneurial discovery and offer distinct conceptual aspects and theoretic propositions instrumental to future social entrepreneurship research.

Split menus: effectively using selection frequency to organize menus

Abstract: When some items in a menu are selected more frequently than others, as is often the case, designers or individual users may be able to speed performance and improve preference ratings by placing several high-frequency items at the top of the menu. Design guidelines for split menus were developed and applied. Split menus were implemented and tested in two in situ usability studies and a controlled experiment. In the usability studies performance times were reduced by 17 to 58% depending on the site and menus. In the controlled experiment split menus were significantly faster than alphabetic menus and yielded significantly higher subjective preferences. A possible resolution to the continuing debate among cognitive theorists about predicting menu selection times is offered. We conjecture and offer evidence that, at least when selecting items from pull-down menus, a logarithmic model applies to familiar (high-frequency) items, and a linear model to unfamiliar (low-frequency) items.

Beyond the Numbers: Measuring the Information Content of Earnings Press Release Language

Abstract: Earnings press releases are the primary mechanism by which managers announce quarterly earnings and make other concurrent disclosures to investors and other stakeholders. A largely unexplored element of earnings press releases is the language that managers use throughout the press release, which we argue provides a unifying framework for these disclosures and an opportunity for managers to signal, both directly and more subtly, their expectations about future performance. We analyze the full texts of approximately 23,000 earnings press releases issued between 1998 and 2003 and examine whether the language used in these earnings press releases provides a signal about expected future firm performance and whether the market responds to this signal. Using categories derived from linguistic theory, we count words characterized as optimistic and pessimistic and construct a measure of managers’ net optimistic language for each earnings press release. We find that this measure is positively associated with future ROA and generates a significant market response in a short window around the earnings announcement date. We include in our models the earnings surprise as well as other quantifiable, concurrent disclosures identified in prior research as associated with the market’s reaction to earnings press releases. Our results support the premise that earnings press release language provides a signal regarding managers’ future earnings expectations to the market and that the market responds to this signal. We interpret our evidence to suggest that managers use language in earnings press releases to communicate credible information about expected future firm performance.

Broken Promises: Equity Sensitivity as a Moderator Between Psychological Contract Breach and Employee Attitudes and Behavior

Abstract: This study examined the moderating role of equity sensitivity in determining the relationship between psychological contract breach and employees' attitudes and behaviors. Entitled individuals were expected to have greater increases in negative affect toward their organization and greater decreases in job satisfaction and organizational citizenship behavior than benevolent individuals following a breach of extrinsic outcomes (i.e., pay, benefits). Conversely, benevolents were expected to respond more negatively than their entitled counterparts following a breach of intrinsic outcomes (i.e., autonomy, growth). Results supported most of the study's propositions. Practical implications as well as directions for future research are discussed.