Pitch Proposal: Recommenders with a Mission - Assessing Diversity in News Recommendations

By helping the user find relevant and important online content, news recommenders have the potential to fulfill a crucial role in a democratic society. Simultaneously, recent concerns about filter bubbles, fake news and selective exposure are symptomatic of the disruptive potential of these digital news recommenders. Recommender systems can make or break filter bubbles, and as such can be instrumental in creating either a more closed or a more open internet. This document details a pitch for an ongoing project that aims to bridge the gap between normative notions of diversity, rooted in democratic theory, and quantitative metrics necessary for evaluating the recommender system. Our aim is to get feedback on a set of proposed metrics grounded in social science interpretations of diversity.

Media Bias in German News Articles: A Combined Approach

Slanted news coverage, also called media bias, can heavily influence how news consumers interpret and react to the news. Models to identify and describe biases have been proposed across various scientific fields, focusing mostly on English media. In this paper, we propose a method for analyzing media bias in German media. We test different natural language processing techniques and combinations thereof. Specifically, we combine an IDF-based component, a specially created bias lexicon, and a linguistic lexicon. We also flexibly extend our lexica by the usage of word embeddings. We evaluate the system and methods in a survey (N = 46), comparing the bias words our system detected to human annotations. So far, the best component combination results in an F$$_{1}$$ 1 score of 0.31 of words that were identified as biased by our system and our study participants. The low performance shows that the analysis of media bias is still a difficult task, but using fewer resources, we achieved the same performance on the same task than recent research on English. We summarize the next steps in improving the resources and the overall results.

An Educational News Dataset for Recommender Systems

Datasets are an integral part of contemporary research on recommender systems. However, few datasets are available for conventional recommender systems and even very limited datasets are available when it comes to contextualized (time and location-dependent) News Recommender Systems. In this paper, we introduce an educational news dataset for recommender systems. This dataset is the refined version of the earlier published Adressa dataset and intends to support the university students in the educational purpose. We discuss the structure and purpose of the refined dataset in this paper.

Enhancing adaptivity via standard dynamic scheduling middleware

This paper makes three contributions to research on QoS-enabled middleware for open distributed real-time embedded (DRE) systems. First, it describes the design and implementation of a dynamic scheduling framework based on the OMG Real-Time CORBA 1.2 specification (RTC1.2) that provides capabilities for (1) propagating QoS parameters and a locus of execution across endsystems via a distributable thread abstraction and (2) enforcing the scheduling of multiple distributable threads dynamically using standard CORBA middleware. Second, it examines the results of empirical studies that show how adaptive dynamic scheduling and management of distributable threads can be enforced efficiently in standard middleware for open DRE systems. Third, it presents results from case studies of multiple adaptive middleware QoS management technologies to monitor and control the quality, timeliness, and criticality of key operations adaptively in a representative DRE avionics system.