ABSTRACT
Sentic computing relies on well-defined affective models of different complexity-polarity to distinguish positive and negative sentiment, for example, or more nuanced models to capture expressions of human emotions. When used to measure communication success, even the most granular affective model combined with sophisticated machine learning approaches may not fully capture an organisation's strategic positioning goals. Such goals often deviate from the assumptions of standardised affective models. While certain emotions such as Joy and Trust typically represent desirable brand associations, specific communication goals formulated by marketing professionals often go beyond such standard dimensions. For instance, the brand manager of a television show may consider fear or sadness to be desired emotions for its audience. This article introduces expansion techniques for affective models, combining common and commonsense knowledge available in knowledge graphs with language models and affective reasoning, improving coverage and consistency as well as supporting domain-specific interpretations of emotions. An extensive evaluation compares the performance of different expansion techniques: (i) a quantitative evaluation based on the revisited Hourglass of Emotions model to assess performance on complex models that cover multiple affective categories, using manually compiled gold standard data, and (ii) a qualitative evaluation of a domain-specific affective model for television programme brands. The results of these evaluations demonstrate that the introduced techniques support a variety of embeddings and pre-trained models. The paper concludes with a discussion on applying this approach to other scenarios where affective model resources are scarce.
ABSTRACT
This paper presents a Web intelligence portal that captures and aggregates news and social media coverage about "Game of Thrones", an American drama television series created for the HBO television network based on George R.R. Martin's series of fantasy novels. The system collects content from the Web sites of Anglo-American news media as well as from four social media platforms: Twitter, Facebook, Google+ and YouTube. An interactive dashboard with trend charts and synchronized visual analytics components not only shows how often Game of Thrones events and characters are being mentioned by journalists and viewers, but also provides a real-time account of concepts that are being associated with the unfolding storyline and each new episode. Positive or negative sentiment is computed automatically, which sheds light on the perception of actors and new plot elements.
ABSTRACT
The aim of this study was to employ neuro-fuzzy logic and regression calculations to determine the accuracy of prediction of the power output ( P) of the maximal lactate steady-state (MLSS) on a cycle ergometer calculated from the results of incremental tests. A group of 17 male and 17 female sports students underwent two incremental tests (a 1 min test T(1): initial exercise intensity 0.2 W x kg(-1) increasing 0.2 W x kg(-1) every minute; a 3 min test T(3): initial exercise intensity 0.6 W x kg(-1) increasing 0.6 W x kg(-1) every 3 min) and at least four constant-intensity tests of 30 min duration. Two models for MLSS calculation were developed using the data from T(1) and T(3), a forward stepwise linear regression model (REG) and a neuro-fuzzy model (FUZ). A group of 26 randomly selected subjects (model group, MG) were used to generate the REG and the FUZ models. The data from the remaining 8 subjects (4 men and 4 women; verifying group, VG) were used to verify the REG and FUZ models. The precision of the MLSS calculation in MG produced a better correlation when using data from T(1) (REG r=0.95, FUZ r=0.99) than data from T(3) (REG r=0.88, FUZ r=0.98). Our calculation models were confirmed using data from VG for T(1) (REG r=0.97, FUZ r=0.98) as well as for T(3) (REG r=0.97, FUZ r=0.97). Based on our subject population of young, healthy sport students, our results suggest that a single incremental test may be used for prediction of P at the MLSS using a cycle ergometer. Furthermore, the results from T(1) yielded higher correlations compared to T(3). Calculations from REG were similar to FUZ but the precision of REG and FUZ was better compared to calculations derived using data from a single threshold.
