Proceedings of the 15th International Conference on Knowledge Technologies and Data-driven Business最新文献

Facilitating maturing of socio-technical patterns through social learning approaches 通过社会学习方法促进社会技术模式的成熟

Proceedings of the 15th International Conference on Knowledge Technologies and Data-driven Business Pub Date : 2015-10-21 DOI: 10.1145/2809563.2809575

Christine Kunzmann, Andreas P. Schmidt, Carmen Wolf

引用次数: 1

Weather-it: evolution of an online community for citizen inquiry Weather-it:公民查询在线社区的演变

Proceedings of the 15th International Conference on Knowledge Technologies and Data-driven Business Pub Date : 2015-10-21 DOI: 10.1145/2809563.2809567

M. Aristeidou, E. Scanlon, M. Sharples

引用次数: 17

Analysis of cyberbullying tweets in trending world events 分析世界热点事件中的网络欺凌推文

Proceedings of the 15th International Conference on Knowledge Technologies and Data-driven Business Pub Date : 2015-10-21 DOI: 10.1145/2809563.2809605

Keith Cortis, S. Handschuh

{"title":"Analysis of cyberbullying tweets in trending world events","authors":"Keith Cortis, S. Handschuh","doi":"10.1145/2809563.2809605","DOIUrl":"https://doi.org/10.1145/2809563.2809605","url":null,"abstract":"The use of social media amongst children, adolescents and families is nowadays a common practise in our everyday lives. Social networking sites allow social interaction between people through various channels, such as Twitter, Facebook, YouTube and blogs. Even if this interaction is generally healthy, these sites bring several risks, such as cyberbullying, depression and exposure of inappropriate content. In this paper we tackle the problem of cyberbullying via a novel approach that analyses online posts in trending world events. These generally cause a lot of interest and controversy among online Web users. Twitter is the social network of choice, where a large dataset of tweets is collected. The two current world events selected are the Ebola virus outbreak in Africa and the shooting of Michael Brown in Ferguson, Missouri. Collected tweets are carefully analysed to identify the most popular hashtags and named entities used within cyberbullying tweets. This analysis provides a basis towards several useful applications, such as a cyberbullying online post detector for certain current trending world events. This will help reduce the number of cyberbullying cases in social networking sites. Results obtained from this evaluation can be applied to other cyberbullying scenarios.","PeriodicalId":20526,"journal":{"name":"Proceedings of the 15th International Conference on Knowledge Technologies and Data-driven Business","volume":"165 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2015-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86207074","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: 23

Search-based entity disambiguation with document-centric knowledge bases 使用以文档为中心的知识库的基于搜索的实体消歧

Proceedings of the 15th International Conference on Knowledge Technologies and Data-driven Business Pub Date : 2015-10-21 DOI: 10.1145/2809563.2809618

Stefan Zwicklbauer, C. Seifert, M. Granitzer

{"title":"Search-based entity disambiguation with document-centric knowledge bases","authors":"Stefan Zwicklbauer, C. Seifert, M. Granitzer","doi":"10.1145/2809563.2809618","DOIUrl":"https://doi.org/10.1145/2809563.2809618","url":null,"abstract":"Entity disambiguation is the task of mapping ambiguous terms in natural-language text to its entities in a knowledge base. One possibility to describe these entities within a knowledge base is via entity-annotated documents (document-centric knowledge base). It has been shown that entity disambiguation with search-based algorithms that use document-centric knowledge bases perform well on the biomedical domain. In this context, the question remains how the quantity of annotated entities within documents and the document count used for entity classification influence disambiguation results. Another open question is whether disambiguation results hold true on more general knowledge data sets (e.g. Wikipedia). In our work we implement a search-based, document-centric disambiguation system and explicitly evaluate the mentioned issues on the biomedical data set CALBC and general knowledge data set Wikipedia, respectively. We show that the number of documents used for classification and the amount of annotations within these documents must be well-matched to attain the best result. Additionally, we reveal that disambiguation accuracy is poor on Wikipedia. We show that disambiguation results significantly improve when using shorter but more documents (e.g. Wikipedia paragraphs). Our results indicate that search-based, document-centric disambiguation systems must be carefully adapted with reference to the underlying domain and availability of user data.","PeriodicalId":20526,"journal":{"name":"Proceedings of the 15th International Conference on Knowledge Technologies and Data-driven Business","volume":"49 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2015-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86605122","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: 2

The power of provisionality: an experimental evaluation of idea appearance in online knowledge creation 临时性的力量:网络知识创造中思想出现的实验评价

Proceedings of the 15th International Conference on Knowledge Technologies and Data-driven Business Pub Date : 2015-10-21 DOI: 10.1145/2809563.2809572

L. McGrath

{"title":"The power of provisionality: an experimental evaluation of idea appearance in online knowledge creation","authors":"L. McGrath","doi":"10.1145/2809563.2809572","DOIUrl":"https://doi.org/10.1145/2809563.2809572","url":null,"abstract":"The software known as creativity support systems (CSS) have become a critical catalyst of the knowledge creation process. Nonaka and Konno integrated CSS into wider knowledge management processes with the concept of ba. Ba are shared spaces in which relationships between knowledge and individuals can develop. This study finds that minor changes to the appearance of icons users interact with in CSS impact user knowledge creation dialogue. Under laboratory conditions, this study uses a 2×2 factorial experiment to investigate the impact of icon and typeface appearance on the idea generation processes of 37 pairs of active managers within a synchronous CSS. Participants used icons which differed on their appearance of finishedness to enter ideas into a shared working space. Some icons looked like rough first drafts, others looked perfectly complete and refined. Participants initial ideas were equally unripe but the icons created different levels of perceived finishedness (PF). Participant ideas were also displayed on-screen using a typeface which was either easy or difficult to cognitively process. Icon PF and typeface processing difficulty level had a crossover interaction effect. A low PF icon and an easy-to-process typeface resulted in more original ideas. Conversely, a high PF icon and a difficult-to-process typeface resulted in less original ideas. These findings and their implications are discussed in terms of enabling spaces, or ba, semantic memory, and difficulty of information processing.","PeriodicalId":20526,"journal":{"name":"Proceedings of the 15th International Conference on Knowledge Technologies and Data-driven Business","volume":"13 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2015-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90242149","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: 1

Data citation quantity and quality in research output of a large-scale educational panel study 大型教育小组研究成果的数据引用数量与质量

Proceedings of the 15th International Conference on Knowledge Technologies and Data-driven Business Pub Date : 2015-10-21 DOI: 10.1145/2809563.2809617

Nadine Mahrholz, Anke Reinhold, Marc Rittberger

引用次数: 0

A platform for contextual multimedia data: towards a unified metadata model and querying 上下文多媒体数据平台:迈向统一的元数据模型和查询

Proceedings of the 15th International Conference on Knowledge Technologies and Data-driven Business Pub Date : 2015-10-21 DOI: 10.1145/2809563.2809586

K. Schlegel, Emanuel Berndl, M. Granitzer, H. Kosch, T. Kurz

{"title":"A platform for contextual multimedia data: towards a unified metadata model and querying","authors":"K. Schlegel, Emanuel Berndl, M. Granitzer, H. Kosch, T. Kurz","doi":"10.1145/2809563.2809586","DOIUrl":"https://doi.org/10.1145/2809563.2809586","url":null,"abstract":"Whereas the former Web mostly consisted of information represented in textual documents, nowadays the Web includes a huge number of multimedia documents like videos, photos, and audio. This enormous increase in volume in the private, and above all in the industry sector, makes it more and more difficult to find relevant information. Besides the pure management of multimedia documents, finding hidden semantics and interconnections of heterogeneous cross-media content is a crucial task and stays mostly untouched. To overcome this tendency we see the need for a generic cross-media analysis platform, ranging from extracting relevant features from media objects over representing and publishing extraction results to integrated querying of aggregated findings. In this paper we propose the underlying foundation for a common and contextual multimedia platform in terms of an unified model for publishing multimedia analysis results. The proposed model is based on existing ontologies, adapted and extended to the cross-media environment. Besides the introduction of the already mentioned platform and model, this paper also briefly introduces specific use-case applications as well as possibilities to query the persisted data.","PeriodicalId":20526,"journal":{"name":"Proceedings of the 15th International Conference on Knowledge Technologies and Data-driven Business","volume":"266 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2015-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76596509","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: 2

A vulnerability's lifetime: enhancing version information in CVE databases 漏洞的生存期:增强CVE数据库中的版本信息

Proceedings of the 15th International Conference on Knowledge Technologies and Data-driven Business Pub Date : 2015-10-21 DOI: 10.1145/2809563.2809612

Leonid Glanz, Sebastian Schmidt, S. Wollny, Ben Hermann

引用次数: 12

Learning from the uncertain: leveraging social communities to generate reliable training data for visual concept detection tasks 从不确定中学习:利用社会群体为视觉概念检测任务生成可靠的训练数据

Proceedings of the 15th International Conference on Knowledge Technologies and Data-driven Business Pub Date : 2015-10-21 DOI: 10.1145/2809563.2809587

C. Hentschel, Harald Sack

{"title":"Learning from the uncertain: leveraging social communities to generate reliable training data for visual concept detection tasks","authors":"C. Hentschel, Harald Sack","doi":"10.1145/2809563.2809587","DOIUrl":"https://doi.org/10.1145/2809563.2809587","url":null,"abstract":"Recent advances for visual concept detection based on deep convolutional neural networks have only been successful because of the availability of huge training datasets provided by benchmarking initiatives such as ImageNet. Assembly of reliably annotated training data still is a largely manual effort and can only be approached efficiently as crowd-working tasks. On the other hand, user generated photos and annotations are available at almost no costs in social photo communities such as Flickr. Leveraging the information available in these communities may help to extend existing datasets as well as to create new ones for completely different classification scenarios. However, user generated annotations of photos are known to be incomplete, subjective and do not necessarily relate to the depicted content. In this paper, we therefore present an approach to reliably identify photos relevant for a given visual concept category. We have downloaded additional metadata for 1 million Flickr images and have trained a language model based on user generated annotations. Relevance estimation is based on accordance of an image's annotation data with our language model and on subsequent visual re-ranking. Experimental results demonstrate the potential of the proposed method -- comparison with a baseline approach based on single tag matching shows significant improvements.","PeriodicalId":20526,"journal":{"name":"Proceedings of the 15th International Conference on Knowledge Technologies and Data-driven Business","volume":"236 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2015-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79703511","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

Fostering open science to research using a taxonomy and an eLearning portal 使用分类法和电子学习门户网站促进开放科学研究

Proceedings of the 15th International Conference on Knowledge Technologies and Data-driven Business Pub Date : 2015-10-21 DOI: 10.1145/2809563.2809571

Nancy Pontika, Petr Knoth, M. Cancellieri, Samuel Pearce

引用次数: 94