Narrative Generation for Suspense: Modeling and Evaluation

Cheong, Yun-Gyung; Young, R. Michael

doi:10.1007/978-3-540-89454-4_21

Cited by 55 publications

(31 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Note that Flow is also correlated with the Positive emotional state (.535). Note also that the scores for Flow and Positive emotional state are, for the first group 2.81 and 3.23 respectively, in a 5-point Likert scale (1)(2)(3)(4)(5), which correspond to rather high values (see [15] for comparisons with other systems tested with the same scales).…”

Section: Results and Interpretation Of Questionnaires-indicators Corrmentioning

confidence: 99%

Objective Metrics for Interactive Narrative

Szilas

Ilea

2014

Interactive Storytelling

View full text Add to dashboard Cite

Abstract. This paper describes, implements and assesses a series of user-log indicators for automatic interactive narrative evaluation. The indicators include length and duration, diversity, renewal, choice range, choice frequency, and choice variety. Based on a laboratory experiment with players, a significant positive correlation has been observed between two indicators and some aspects of the interactive narrative experience measured by validated scales based on questionnaires.

show abstract

Section: Results and Interpretation Of Questionnaires-indicators Corrmentioning

confidence: 99%

Objective Metrics for Interactive Narrative

Szilas

Ilea

2014

Interactive Storytelling

View full text Add to dashboard Cite

show abstract

“…The error bars show one standard deviation based on 9 repeats over 3 narrative initial states. The high variance is to be expected, as narrative spaces are well known to be non-uniform [9].…”

Section: Generative Powermentioning

confidence: 99%

Generating story variants with constrained video recombination

Piacenza

Guerrini

Adami

et al. 2011

Proceedings of the 19th ACM International Conference on Multimedia

View full text Add to dashboard Cite

We present a novel approach to the automatic generation of filmic variants within an implemented Video-Based Storytelling (VBS) system that successfully integrates video segmentation with stochastically controlled re-ordering techniques and narrative generation via AI planning. We have introduced flexibility into the video recombination process by sequencing video shots in a way that maintains local video consistency and this is combined with exploitation of shot polysemy to enable shot reuse in a range of valid semantic contexts. Results of evaluations on output narratives using a shared set of video data show consistency in terms of local video sequences and global causality with no loss of generative power.

show abstract

“…Plan-based models have also been used to achieve other discourse phenomena, such as suspense (Cheong & Young, 2008), surprise (Bae & Young, 2014), and cinematic composition (Jhala & Young, 2010). As with these other models of discourse, Indexter can inform story generation as well as discourse generation.…”

Section: Chapter 2 -Related Workmentioning

confidence: 99%