A huge number of informal messages are posted every day in social network sites, blogs and discussion forums. Emotions seem to be frequently important in these texts for expressing friendship, showing social support or as part of online arguments. Algorithms to identify sentiment and sentiment strength are needed to help understand the role of emotion in this informal communication and also to identify inappropriate or anomalous affective utterances, potentially associated with threatening behaviour to the self or others. Nevertheless, existing sentiment detection algorithms tend to be commercially-oriented, designed to identify opinions about products rather than user behaviours. This article partly fills this gap with a new algorithm, SentiStrength, to extract sentiment strength from informal English text, using new methods to exploit the de-facto grammars and spelling styles of cyberspace. Applied to MySpace comments and with a lookup table of term sentiment strengths optimised by machine learning, SentiStrength is able to predict positive emotion with 60.6 % accuracy and negative emotion with 72.8 % accuracy, both based upon strength scales of 1-5. The former, but not the latter, is better than baseline and a wide range of general machine learning approaches.

Abstract not found

On behalf of:

Abstract. The human face plays a central role in most forms of natural human interaction so we may expect that computational methods for analysis of facial information and graphical and robotic methods for synthesis of faces and facial expressions will play a growing role in human-computer and human-robot interaction. However, certain areas of face-based HCI, such as facial expression recognition and robotic facial display have lagged others, such as eye-gaze tracking, facial recognition, and conversational characters. Our goal in this paper is to review the situation in HCI with regards to the human face, and to discuss strategies which could bring more slowly developing areas up to speed.

Research in expressing continuous emotional response to music as a function of its psychoacoustic parameters: Current and future directions. Continuous response of emotion in music is undergoing a boom. One application of this kind of research is to gain further insight into the relationship between musical/psychoacoustic parameters and associated emotional responses. Continuous response methodology has potential to produce major new insights into these relationships, however there are pitfalls and challenges associated with it. The present paper discusses some of the methodological issues that may be hindering progress. Many of the problems stem from the complex, interdisciplinary nature of this kind of research. In the past I have, for example, commented on some of the statistical issues and concerns. In this paper I will discuss problems the measurement of psychoacoustic/musical parameters, and in coding and relating them back to the emotional perception. There are various issues that require consideration regarding the coding of loudness, pitch, articulation, spectral centroid, harmony and so forth, some of which appear to be unresolved in the literature concerned with emotional response: What kind of loudness algorithm should be used, how can melody, harmony, articulation and so forth be coded and sampled, how should centroid be measured, and what is the relationship between the psychoacoustic and perceptual (nonemotional) parameters? What kinds of visual aids can be used to assist with analysis? In addressing some of these issues, I conclude that researchers need to incorporate new methodologies and be cognizant of potential problems. 1.

On behalf of:

Abstract not found

This paper explores the role of social capital in human resources management. We suggest that the recent interest in social capital has neglected the possibility that social networks may contain negative ties, and that attention to these negative ties may provide additional insights into understanding relationships and social networks in organizations. Research focusing on the antecedents and consequences of social networks in organizations is reviewed. We consider the effects of the "social ledger" (social capital and negative relationships) on "social" resources management outcomes such as recruitment, selection, socialization, training, performance, career development, turnover, job satisfaction,