Workshop on Computational Models of Narrative最新文献

{"title":"Structured Narratives as a Framework for Journalism: A Work in Progress","authors":"David A. Caswell","doi":"10.4230/OASIcs.CMN.2015.39","DOIUrl":"https://doi.org/10.4230/OASIcs.CMN.2015.39","url":null,"abstract":"This paper describes Structured Stories, a platform for producing and consuming journalism as structured narratives based on instantiations of event frames. The event frames are defined using FrameNet and are instantiated as structured events using references to nodes in various knowledge graphs. Structured narratives with recursive, fractal and network characteristics are then assembled from these structured events. The approach requires the direct reporting of journalistic events into structure by untrained reporters, and utilizes a simplified sequential user interface to achieve this. A prototype has been built and published, and is being applied to the reporting of local government journalism to explore editorial aspects of the approach.","PeriodicalId":311534,"journal":{"name":"Workshop on Computational Models of Narrative","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114701190","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Character Networks for Narrative Generation: Structural Balance Theory and the Emergence of Proto-Narratives","authors":"G. Sack","doi":"10.4230/OASIcs.CMN.2013.183","DOIUrl":"https://doi.org/10.4230/OASIcs.CMN.2013.183","url":null,"abstract":"This paper models narrative as a complex adaptive system in which the temporal sequence of events constituting a story emerges out of cascading local interactions between nodes in a social network. The approach is not intended as a general theory of narrative, but rather as a particular generative mechanism relevant to several academic communities: (1) literary critics and narrative theorists interested in new models for narrative analysis, (2) artificial intelligence researchers and video game designers interested in new mechanisms for narrative generation, and (3) complex systems theorists interested in novel applications of agent-based modeling and network theory. The paper is divided into two parts. The first part offers examples of research by literary critics on the relationship between social networks of fictional characters and the structure of long-form narratives, particularly novels. The second part provides an example of schematic story generation based on a simulation of the structural balance network model. I will argue that if literary critics can better understand sophisticated narratives by extracting networks from them, then narrative intelligence researchers can benefit by inverting the process, that is, by generating narratives from networks.","PeriodicalId":311534,"journal":{"name":"Workshop on Computational Models of Narrative","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121825063","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Paradigm for Eliciting Story Variation","authors":"Bernhard Fisseni, F. Lawrence","doi":"10.4230/OASIcs.CMN.2013.100","DOIUrl":"https://doi.org/10.4230/OASIcs.CMN.2013.100","url":null,"abstract":"The understanding of story variation, whether motivated by cultural currents or other factors, is important for applications of formal models of narrative such as story generation or story retrieval. We present the first stage of an experiment to elicit natural narrative variation data suitable for evaluation with respect to story similarity, to qualitative and quantitative analysis of story variation, and also for data processing. We also present few prelimary results from the first stage of the experiment, using Red Riding Hood and Romeo and Juliet as base texts.","PeriodicalId":311534,"journal":{"name":"Workshop on Computational Models of Narrative","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127847952","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Story Comparisons: Evidence from Film Reviews","authors":"Bernhard Fisseni, Aadil Kurji, Deniz Sarikaya, Mira Viehstädt","doi":"10.4230/OASIcs.CMN.2013.94","DOIUrl":"https://doi.org/10.4230/OASIcs.CMN.2013.94","url":null,"abstract":"Interested in formally modelling similarity between narratives, we \u0000investigate judgements of similarity between narratives in a small \u0000corpus of film reviews and book–film comparisons. A main finding is \u0000that judgements tend to concern multiple levels of story \u0000representation at once. As these texts are pragmatically related to \u0000reception contexts, we find many references to reception quality and \u0000optimality. We conclude that current formal models of narrative can \u0000not capture the task of naturalistic narrative comparisons given in \u0000the analysed reviews, but that the development of models containing a \u0000more reception-oriented point of view will be necessary.","PeriodicalId":311534,"journal":{"name":"Workshop on Computational Models of Narrative","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133455154","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Trailer Brain: Neural and Behavioral Analysis of Social Issue Documentary Viewing with Low-Density EEG","authors":"Jason Sherwin, C. Brenner, John S. Johnson","doi":"10.4230/OASIcs.CMN.2016.2","DOIUrl":"https://doi.org/10.4230/OASIcs.CMN.2016.2","url":null,"abstract":"The effects of social issue documentaries are diverse. In particular, monetary donations and advocacy on social media are behavioral effects with public consequences. Conversely, information-seeking about an issue is potentially done in private. We designed a combined free-viewing and rapid perceptual decision-making experiment to simulate a real scenario confronted by otherwise uninformed movie-viewers, i.e., to determine what degree of support they will lend to a film based on its trailer. For a cohort of subjects with active video-streaming (e.g., Netflix) and social media accounts (e.g., Facebook), we recorded electroencephalography (EEG) and behavioral responses to trailers of social issue documentaries. We examined EEG using reliable component analysis (RCA), finding reliability within subjects across multiple viewings and across subjects within a given viewing of the same trailer. We found this reliability both over EEG captured from whole-movie viewing, as well as over 5-second movie segments. Behavioral responses following trailer viewing were not consistent from first to second viewings. Rather, support choices both tended towards extremes of support/non-support and were made faster upon second viewing. We hypothesized a relationship between reliability behavioral metrics, finding credible evidence for it in this dataset. Finally, we found that we could suitably train a naive classifier to categorize production value and narrative voice ratings given to the viewed movies from RCA-based metrics alone. In sum, our results show that EEG components during free-viewing of social issue documentary trailers can provide a useful tool to investigate viewers' neural responses during viewing, when coupled with a post hoc behavioral decision-making paradigm. The possibility of this tool being used by producers and filmmakers is also discussed.","PeriodicalId":311534,"journal":{"name":"Workshop on Computational Models of Narrative","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130166456","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Imaginative Recall with Story Intention Graphs","authors":"Sarah Harmon, A. Jhala","doi":"10.4230/OASIcs.CMN.2015.72","DOIUrl":"https://doi.org/10.4230/OASIcs.CMN.2015.72","url":null,"abstract":"Intelligent storytelling systems either formalize specific narrative structures proposed by narratologists (such as Propp and Bremond), or are founded on formal representations from artificial intelligence (such as plan structures from classical planning). This disparity in underlying knowledge representations leads to a lack of common evaluation metrics across story generation systems, particularly around the creativity aspect of generators. This paper takes Skald, a reconstruction of the Minstrel creative story generation system, and maps the representation to a formal narrative representation of Story Intention Graphs (SIG) proposed by Elson et al. This mapping facilitates the opportunity to expand the creative space of stories generated through imaginative recall in Minstrel while maintaining narrative complexity. We show that there is promise in using the SIG as an intermediate representation that is useful for evaluation of story generation systems.","PeriodicalId":311534,"journal":{"name":"Workshop on Computational Models of Narrative","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134010470","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Narrativity and Textuality in the Study of Stories","authors":"Moshe Simon-Shoshan","doi":"10.4230/OASIcs.CMN.2013.228","DOIUrl":"https://doi.org/10.4230/OASIcs.CMN.2013.228","url":null,"abstract":"This paper seeks to investigate some of the defining elements of \u0000narrative. The underlying assumption of my discussion is that the \u0000terms \"narrative\" and \"story\" do not refer to clearly defined, \u0000self-enclosed genres. Rather, they are part of a spectrum which \u0000embraces all forms of texts. Similarly, narratives and stories are not \u0000independent discourses but rather are an integral part of virtually \u0000all forms of discourse, be it day-to-day conversation or more \u0000specialized discourses. In order to analyze the relationship between \u0000narratives and other modes of discourse, we introduce the concept of \u0000narrativity. Narrativity refers to a collection of textual attributes. \u0000All texts exist along a continuum of greater or lesser narrativity, \u0000depending on the number and prominence of the narrative attributes \u0000they contain. When we refer to a text as a story, we mean that it \u0000contains a critical mass of narrativity. Most theorists of narrative \u0000have defined narrativity purely in terms of \"dynamism\" - that is, the \u0000extent to which a text portrays transition and change. To this I have \u0000added the quality of \"specificity\". Specificity refers to the extent \u0000to which a text focuses on a particular time or place, a unique event, \u0000or individual people and objects. Many if not most texts contain a \u0000certain degree of narrativity. We established, however, that in order \u0000to be considered a story the text must present a sequence of at least \u0000two interrelated events that occurred once and only once in the past. \u0000In other words, a story must have a certain degree of dynamism in that \u0000it portrays the transition from at least one event to another. It must \u0000also have specificity at least to the degree that the text narrates \u0000events that happened at a fixed time in the past. This theoretical \u0000framework allows us to chart the relationship between different types \u0000of texts within a single discourse. It also gives us a vocabulary for \u0000discussing different parts of more complex narratives which often \u0000contain elements of varying narrativity. The paper then goes on to \u0000discuss the concept of narrative structure, arguing that narrative \u0000structure is not an inherent attribute of narrative texts but a \u0000framework that the reader imposes on the text in order to make it \u0000intelligible in terms of other narratives. The structure which the \u0000reader abstracts from a given narrative will be heavily dependent on \u0000the context of the narrative with in a wider discourse.","PeriodicalId":311534,"journal":{"name":"Workshop on Computational Models of Narrative","volume":"151 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133803622","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Gathering Background Knowledge for Story Understanding through Crowdsourcing","authors":"Christos T. Rodosthenous, Loizos Michael","doi":"10.4230/OASIcs.CMN.2014.154","DOIUrl":"https://doi.org/10.4230/OASIcs.CMN.2014.154","url":null,"abstract":"Successfully comprehending stories involves integration of the story information with the reader’s own background knowledge. A prerequisite, then, of building automated story understanding systems is the availability of such background knowledge. We take the approach that knowledge appropriate for story understanding can be gathered by sourcing the task to the crowd. Our methodology centers on breaking this task into a sequence of more specific tasks, so that human participants not only identify relevant knowledge, but also convert it into a machine-readable form, generalize it, and evaluate its appropriateness. These individual tasks are presented to human participants as missions in an online game, oering them, in this manner, an incentive for their participation. We report on an initial deployment of the game, and discuss our ongoing work for integrating the knowledge gathering task into a full-fledged story understanding engine. 1998 ACM Subject Classification I.2.4 Knowledge Representation Formalisms and Methods","PeriodicalId":311534,"journal":{"name":"Workshop on Computational Models of Narrative","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114428092","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Towards Empathic Neurofeedback for Interactive Storytelling","authors":"M. Cavazza, Gabor Aranyi, Fred Charles, J. Porteous, Stephen W. Gilroy, Ilana Klovatch, Gilan Jackont, E. Soreq, Nimrod Jakob Keynan, Avihay Cohen, G. Raz, T. Hendler","doi":"10.4230/OASIcs.CMN.2014.42","DOIUrl":"https://doi.org/10.4230/OASIcs.CMN.2014.42","url":null,"abstract":"Interactive Narrative is a form of digital entertainment based on AI techniques which support narrative generation and user interaction. Despite recent progress in the field, there is still a lack of unified models integrating narrative generation, user response and interaction. This paper addresses this issue by revisiting existing Interactive Narrative paradigms, granting explicit status to users' disposition towards story characters. We introduce a novel Brain-Computer Interface (BCI) design, which attempts to capture empathy for the main character in a way that is compatible with filmic theories of emotion. Results from two experimental studies with a fully-implemented system demonstrate the effectiveness of a neurofeedback-based approach, showing that subjects can successfully modulate their emotional support for a character who is confronted with challenging situations. A preliminary fMRI analysis also shows activation during user interaction, in regions of the brain associated with emotional control.","PeriodicalId":311534,"journal":{"name":"Workshop on Computational Models of Narrative","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128811797","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Character Model with Moral Emotions: Preliminary Evaluation","authors":"C. Battaglino, R. Damiano","doi":"10.4230/OASIcs.CMN.2014.24","DOIUrl":"https://doi.org/10.4230/OASIcs.CMN.2014.24","url":null,"abstract":"In literary and drama criticism, emotions, and moral emotions in particular, have been pointed out as one of characterizing features of stories. In this paper, we propose to model story characters as value-based emotional agents, who appraise their own and others' actions based on their desires and values, and feel the appropriate moral emotions in response to narrative situations that challenge their goals and values. \u0000 \u0000In order to validate the appropriateness of the agent model for narrative characters, we ran an experiment with human participants aimed at comparing their expectations about characters' emotions with the predictions of the value-based model of emotional agent. The results of the experiment show that the participants' expectations meet the predictions of the model.","PeriodicalId":311534,"journal":{"name":"Workshop on Computational Models of Narrative","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122594857","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}