Proceedings of the 31st ACM Conference on Hypertext and Social Media最新文献_第4页

Visually-Aware Video Recommendation in the Cold Start 冷启动中的视觉感知视频推荐

Proceedings of the 31st ACM Conference on Hypertext and Social Media Pub Date : 2020-07-13 DOI: 10.1145/3372923.3404778

Mehdi Elahi, Reza Hosseini, Mohammad Hossein Rimaz, Farshad Bakhshandegan Moghaddam, C. Trattner

{"title":"Visually-Aware Video Recommendation in the Cold Start","authors":"Mehdi Elahi, Reza Hosseini, Mohammad Hossein Rimaz, Farshad Bakhshandegan Moghaddam, C. Trattner","doi":"10.1145/3372923.3404778","DOIUrl":"https://doi.org/10.1145/3372923.3404778","url":null,"abstract":"Recommender Systems have become essential tools in any modern video-sharing platform. Although, recommender systems have shown to be effective in generating personalized suggestions in video-sharing platforms, however, they suffer from the so-called New Item problem. New item problem, as part of Cold Start problem, happens when a new item is added to the system catalogue and the recommender system has no or little data available for that new item. In such a case, the system may fail to meaningfully recommend the new item to the users. In this paper, we propose a novel recommender system that is based on visual tags, i.e., tags that are automatically annotated to videos based on visual description of the videos. Such visual tags can be used in an extreme cold start situation, where neither any rating, nor any tag is available for the new video. The visual tags could also be used in the moderate cold start situation when the new video might have been annotated with few tags. This type of content features can be extracted automatically without any human involvement and have been shown to be very effective in representing the video content. We have used a large dataset of videos and shown that automatically extracted visual tags can be incorporated into the cold start recommendation process and achieve superior results compared to the recommendation based on human-annotated tags.","PeriodicalId":389616,"journal":{"name":"Proceedings of the 31st ACM Conference on Hypertext and Social Media","volume":"89 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117314607","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}

引用次数: 7

Hacking Droids and Casting Spells: Locative Augmented Reality Games and the Reimagining of the Theme Park 破解机器人和施法:位置增强现实游戏和主题公园的重新想象

Proceedings of the 31st ACM Conference on Hypertext and Social Media Pub Date : 2020-07-13 DOI: 10.1145/3372923.3404801

Raymond T. Eddy, Carissa Baker, R. Macy, John Murray, Anastasia Salter

引用次数: 1

Docuverse Despatch: Information Farming for the Collective 文献传送:集体的信息农场

Proceedings of the 31st ACM Conference on Hypertext and Social Media Pub Date : 2020-07-13 DOI: 10.1145/3372923.3404774

Mark W. R. Anderson

引用次数: 0

The Hypertext Years? 超文本时代?

Proceedings of the 31st ACM Conference on Hypertext and Social Media Pub Date : 2020-07-13 DOI: 10.1145/3372923.3404478

Stuart Moulthrop

{"title":"The Hypertext Years?","authors":"Stuart Moulthrop","doi":"10.1145/3372923.3404478","DOIUrl":"https://doi.org/10.1145/3372923.3404478","url":null,"abstract":"This talk begins with the crazy notion that we might think of hypertext as a signature for the period 1985-2020. The claim is more plausible technically than culturally, but the talk is perversely addressed to culture. Among other things, the discussion revisits Moulthrop's previous ACM Hypertext keynote in 1998, in which he distinguished between \"exoteric\" hypertext - the then-novel adaptation of the World Wide Web by Amazon and other online retailers - and \"esoteric\" applications in things like hypertext fiction and digital art. The talk updates this insight with reference to later developments such as Jill Walker's \"feral hypertext\" thesis, the rise of social media, and the recognition of computer games as legitimate channels of ideas. While these phenomena have arguably displaced hypertextuality in the popular imagination, Moulthrop points to the major interest in complex narratives, counterfactuals, and multiverses as places where the hypertext aesthetic survives. Turning from aesthetics back to the technical, the talk focuses on Twine, the popular text-gaming application that marries what Alexander Galloway would call the \"proctological\" openness of web technologies with the structure-mapping affordances of graphical hypertext systems. In some ways portraying Twine as a second coming of hypertext is a clear and perhaps intentional misreading. The talk ends by wondering what this misreading might reveal.","PeriodicalId":389616,"journal":{"name":"Proceedings of the 31st ACM Conference on Hypertext and Social Media","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117112660","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}

引用次数: 0

Dash 破折号

Proceedings of the 31st ACM Conference on Hypertext and Social Media Pub Date : 2020-07-13 DOI: 10.1145/3372923.3404807

Stanley Yip, Bob Zeleznik, Samuel Wilkins, Tyler Schicke, A. van Dam

引用次数: 1

Kurios

Proceedings of the 31st ACM Conference on Hypertext and Social Media Pub Date : 2020-07-13 DOI: 10.1145/3372923.3404811

Cameron Tolentino, M. Mosher

引用次数: 2

Games, Hypertext, and Meaning 游戏、超文本和意义

Proceedings of the 31st ACM Conference on Hypertext and Social Media Pub Date : 2020-07-13 DOI: 10.1145/3372923.3404477

Noah Wardrip-Fruin

{"title":"Games, Hypertext, and Meaning","authors":"Noah Wardrip-Fruin","doi":"10.1145/3372923.3404477","DOIUrl":"https://doi.org/10.1145/3372923.3404477","url":null,"abstract":"It might seem that games can address almost any topic. There are versions of Monopoly and Tetris that, alone, seem to address subjects ranging from pop music, bass fishing, and sex to mass murder, slavery, and predatory real estate development. Yet for all but the last of these, the actual play of these games is at odds with the intended theme. So what topics can games meaningfully address? One powerful way that games can address topics is by having playable models that resonate with their intended themes. Monopoly is actually an example of such a game, with a playable model of real estate development ripped off from a game intended as a critique of capitalism's approach to resources. So is the less philosophical DOOM, with playable models of combat and space that match its \"death travelogue\" theme. The foundation of any playable model is a set of operational logics, which combine communication and computation with opportunities for play. (Monopoly's real estate model includes resource, pattern matching, and chance logics.) Video games depend on a relatively small vocabulary of such logics [1]. This restricts the playable models available, which is a challenge faced by those seeking to meaningfully address personal, cultural, and political topics through games [2]. One conspicuous counter-example, however, is the linking logic. The communicative role of the hypertext link is flexible enough that it can be used to address a wide range of topics. Yet the very flexibility of linking logics pushes the burden of systemic use onto game developers, which itself produces limits. Greater connection between video game research and hypertext research communities could be a path to address this.","PeriodicalId":389616,"journal":{"name":"Proceedings of the 31st ACM Conference on Hypertext and Social Media","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125845899","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}

引用次数: 0

Towards Personalized Annotation of Webpages for Efficient Screen-Reader Interaction 面向个性化网页注释，实现高效的屏幕阅读器交互

Proceedings of the 31st ACM Conference on Hypertext and Social Media Pub Date : 2020-07-13 DOI: 10.1145/3372923.3404815

H. Lee, V. Ashok

{"title":"Towards Personalized Annotation of Webpages for Efficient Screen-Reader Interaction","authors":"H. Lee, V. Ashok","doi":"10.1145/3372923.3404815","DOIUrl":"https://doi.org/10.1145/3372923.3404815","url":null,"abstract":"To interact with webpages, people who are blind use special-purpose assistive technology, namely screen readers that enable them to serially navigate and listen to the content using keyboard shortcuts. Although screen readers support a multitude of shortcuts for navigating over a variety of HTML tags, it has been observed that blind users typically rely on only a fraction of these shortcuts according to their personal preferences and knowledge. Thus, a mismatch between a user's repertoire of shortcuts and a webpage markup can significantly increase browsing effort even for simple everyday web tasks. Also, inconsistent usage of ARIA coupled with the increased adoption of styling and semantic HTML tags (e.g., , ) for which there is limited screen-reader support, further make interaction arduous and frustrating for blind users. To address these issues, in this work, we explore personalized annotation of webpages that enables blind users to efficiently navigate webpages using their preferred shortcuts. Specifically, our approach automatically injects personalized 'annotation' nodes into the existing HTML DOM such that blind users can quickly access certain semantically-meaningful segments (e.g., menu, search results, filter options, calendar widget, etc.) on the page, using their preferred screen-reader shortcuts. Using real shortcut profiles collected from 5 blind screen-reader users doing representative web tasks, we observed that with personalized annotation, the interaction effort can be potentially reduced by as much as 48 (average) shortcut presses.","PeriodicalId":389616,"journal":{"name":"Proceedings of the 31st ACM Conference on Hypertext and Social Media","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129060294","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}

引用次数: 0

Thoughts Reflection Machine 思想反射机

Proceedings of the 31st ACM Conference on Hypertext and Social Media Pub Date : 2020-07-13 DOI: 10.1145/3372923.3404837

Claus Atzenbeck, Daniel Roßner

引用次数: 2

Games/Hypertext 游戏/超文本

Proceedings of the 31st ACM Conference on Hypertext and Social Media Pub Date : 2020-07-13 DOI: 10.1145/3372923.3404775

D. Millard

{"title":"Games/Hypertext","authors":"D. Millard","doi":"10.1145/3372923.3404775","DOIUrl":"https://doi.org/10.1145/3372923.3404775","url":null,"abstract":"The relationship between hypertext research and games design is not clear, despite the striking similarity between literary hypertexts and narrative games. This matters as different communities are now exploring hypertext, interactive fiction, electronic literature, and narrative games from different perspectives - but lack a common critical vocabulary or shared body of work with which they can communicate. In this paper I attempt to deconstruct the relationship between literary hypertext and narrative games. I do this through two lenses. Firstly, by looking at Hypertext as Games; with a specific set of mechanics based around textual lexia and link-following (but with a tradition of exploring alternative Strange Hypertext approaches) resulting in a dynamic of exploration and puzzle solving depending on whether agency is expressed at the level of Syuzhet or Fabula. Secondly, by looking at Games as Hypertexts; that depend heavily on textual content, use guard fields, patterns, and sculptural hypertext models to manage agency, that experiment with aporia and epiphany, and that take place within a wider interlinked transmedia experience. This analysis reveals that Narrative Games are both more and less than Hypertext, with a wider set of mechanics and interfaces, but possessed of a core hypertextuality and situated within a greater hypertext context. This suggests that there is much value to be gained from interactions between the communities invested in interactive narrative, and significant potential in the cross-pollination of ideas.","PeriodicalId":389616,"journal":{"name":"Proceedings of the 31st ACM Conference on Hypertext and Social Media","volume":"71 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133861568","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}

引用次数: 3