More than Bags of Words: Sentiment Analysis with Word Embeddings

ABSTRACT

Moving beyond the dominant bag-of-words approach to sentiment analysis we introduce an alternative procedure based on distributed word embeddings. The strength of word embeddings is the ability to capture similarities in word meaning. We use word embeddings as part of a supervised machine learning procedure which estimates levels of negativity in parliamentary speeches. The procedure’s accuracy is evaluated with crowdcoded training sentences; its external validity through a study of patterns of negativity in Austrian parliamentary speeches. The results show the potential of the word embeddings approach for sentiment analysis in the social sciences.     

Counseling With HEART: A Relationship Violence Prevention Program for College Students

Relationship violence is a salient concern on college campuses today, and psychoeducational groups may be an appropriate prevention format. This article describes a study measuring the impact of college student participation in the HEART (Help End Abusive Relationships Today) program, a series of group sessions designed to increase knowledge and awareness of relationship violence. Findings indicated significant changes for group participants postintervention. Implications and recommendations for college counselors are discussed.     

Unfair play in World Cup qualification? An analysis of the 1998–2010 FIFA World Cup performances and the bias in the allocation of tournament berths

This paper reviews the FIFA World Cups 1998–2010 with data available from the FIFA website and assesses the performance of each region in relation to the number of World Cup qualifications spots that the region is awarded. We raise the issue of whether FIFA should be more concerned with the participation of more members from its federations in the World Cup than the financial gain from doing so. Our non-econometric analysis illustrates that the current allocation may be resulting in the awarding of qualification spots to teams that if not unfair, certainly warrants discussion. We seek to demonstrate that the current system of qualification is based neither on ensuring the qualification of the best 32 teams in the world, nor does it fairly allocate qualification spots on the number of teams per federation or any other metric. We conclude with a plea for more transparent allocation processes.