J. Web Sci.最新文献

{"title":"Exploring the Relationship between User Activities and Profile Images on Twitter through Machine Learning Techniques","authors":"T. Tominaga, Y. Hijikata","doi":"10.1561/106.00000015","DOIUrl":"https://doi.org/10.1561/106.00000015","url":null,"abstract":"Social media profile images are one of many visual components of users. Moreover, user activities such as posting or chatting are regarded as self-expression behaviors. In this study, we examine Japanese Twitter users to explore the relationship between user activities and profile images. Logistic regression analysis is used to statistically identify and quantify relationships, leading us to conclude that several profile image categories significantly correlate with user activities. Furthermore, we use machine learning techniques (logistic regression, random forest, and support vector machine) to predict whether or not a user belongs to a specific profile image category. Each model's performance is evaluated and compared for all profile image categories. Primary results show that users whose profile image includes others' faces are more likely to use a replying function but less likely to add url links to their tweets, and that it is the easiest for machine learning models to find their category from their user activities. In short, our findings indicate that visual expression correlates with social media user behavior.","PeriodicalId":405637,"journal":{"name":"J. Web Sci.","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127004784","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":"Multi-Cultural Interlinking of Web Taxonomies with ACROSS","authors":"N. Boldyrev, M. Spaniol, G. Weikum","doi":"10.1561/106.00000012","DOIUrl":"https://doi.org/10.1561/106.00000012","url":null,"abstract":"The Web hosts a huge variety of multi-cultural taxonomies. They encompass product catalogs of e-commerce, general-purpose knowledge bases and numerous domain-specific category systems. The enormous heterogeneity of those sources is a challenging aspect when multiple taxonomies have to be interlinked. In this paper we introduce ACROSS system to support the alignment of independently created Web taxonomies. For mapping categories across different taxonomies, ACROSS harnesses instance-level features as well as distant supervision from an intermediate source like multiple Wikipedia editions. ACROSS includes a reasoning step, which is based on combinatorial optimization. In order to reduce the run time of the reasoning procedure without sacrificing the quality, we study two models of user involvement. Our experiments with heterogeneous taxonomies for different domains demonstrate the viability of our approach and improvement over state-of-the-art baselines.","PeriodicalId":405637,"journal":{"name":"J. Web Sci.","volume":"236 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-02-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115996167","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":"Identity Assurance in the UK: technical implementation and legal implications under eIDAS","authors":"Niko Tsakalakis, Sophie Stalla-Bourdillon, K. O’Hara","doi":"10.1561/106.00000010","DOIUrl":"https://doi.org/10.1561/106.00000010","url":null,"abstract":"Gov.UK Verify, the new Electronic Identity (eID) Management system of the UK Government, has been promoted as a state-of-the-art privacy-preserving system, designed around demands for better privacy and control, and is the first eID system in which the government delegates the provision of identity to competing private third parties. Under the EU eIDAS, Member States can allow their citizens to transact with foreign services by notifying their national eID systems. Once a system is notified, all other Member States are obligated to incorporate it into their electronic identification procedures. The paper offers a discussion of Gov.UK Verify's compliance with eIDAS as well as Gov.UK Verify's potential legal equivalence to EU systems under eIDAS as a third-country legal framework after Brexit. To this end it examines the requirements set forth by eIDAS for national eID systems, classifies these requirements in relation to their ratio legis and organises them into five sets. The paper proposes a more thorough framework than the current regime to decide on legal equivalence and attempts a first application in the case of Gov.UK Verify. It then assesses Gov.UK Verify's compliance against the aforementioned set of requirements and the impact of the system's design on privacy and data protection. The article contributes to relevant literature of privacy{preserving eID management by offering policy and technical recommendations for compliance with the new Regulation and an evaluation of interoperability under eIDAS between systems of different architecture. It is also, to our knowledge, the first exploration of the future of eID management in the UK after a potential exit from the European Union.","PeriodicalId":405637,"journal":{"name":"J. Web Sci.","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-12-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121206635","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 Understanding the Consumption of Video-Ads on YouTube","authors":"Mariana Arantes, F. Figueiredo, J. Almeida","doi":"10.1561/106.00000011","DOIUrl":"https://doi.org/10.1561/106.00000011","url":null,"abstract":"Being the most popular online video platform nowadays, YouTube is a complex ecosystem that generates billions of dollars of revenue yearly. This revenue mostly stems from online advertisements that are shown on the website. Like other social media platforms, YouTube enables any user to create and upload content, create ad-campaigns that promote advertisement content, as well as monetize channels (i.e., YouTube video uploaders) by showing ads from other channels to viewers. More importantly, any individual can watch videos for free and, in consequence, be exposed to advertisements. The mediation of these different parties that interact through ads, as well as the YouTube platform itself is done by online ad auction algorithms. In this paper, we study the aforementioned ecosystem through the use of advertisements in the form of video (video-ads). Online video-ads are a novel medium that is gaining significant traction on social media platforms like YouTube. Our study presents insights on (1) the behavior of users when exposed to video-ads; (2) the popularity of the video-ads over time; (3) the relation between contextual advertising and the effectiveness of ads; (4) the success of ads in generating revenue; and, (5) the success of channels in attracting revenue as exposers of ads. The results here presented have practical implications for content providers, creators, channels, and YouTube viewers.","PeriodicalId":405637,"journal":{"name":"J. Web Sci.","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132180831","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":"Predicting Online Islamophobic Behavior after #ParisAttacks","authors":"Kareem Darwish, Walid Magdy, Afshin Rahimi, Timothy Baldwin, Norah Abokhodair","doi":"10.1561/106.00000013","DOIUrl":"https://doi.org/10.1561/106.00000013","url":null,"abstract":"The Paris terrorist attacks occurred on November 13, 2015, prompting a massive response on social media including Twitter, with millions of posted tweets in the first few hours after the attacks. Most of the tweets were condemning the attacks and showing support to Parisians. One of the trending debates related to the attacks concerned possible association between terrorism and Islam, and Muslims in general. This created a global discussion between those attacking and those defending Islam and Muslims. In this paper, we use this incident to examine the effect of online social network interactions prior to an event to predict what attitudes will be expressed in response to the event. Specifically, we focus on how a person's online content and network dynamics can be used to predict future attitudes and stance in the aftermath of a major event. In our study, we collected a set of 8.36 million tweets related to the Paris attacks within the 50 hours following the event, of which we identified over 900k tweets mentioning Islam and Muslims. We quantitatively analyzed users' network interactions and historical tweets to predict their attitudes towards Islam and Muslim. We provide a description of the quantitative results based on the content (hashtags) and network interactions (retweets, replies, and mentions). We analyze two types of data: (1) we use post-event tweets to learn users' stated stance towards Muslims based on sampling methods and crowd-sourced annotations; and (2) we employ pre-event interactions on Twitter to build a classifier to predict post-event stance. We found that pre-event network interactions can predict attitudes towards Muslims with 82% macro F-measure, even in the absence of prior mentions of Islam, Muslims, or related terms.","PeriodicalId":405637,"journal":{"name":"J. Web Sci.","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132251972","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":"Spreading One's Tweets: How Can Journalists Gain Attention for their Tweeted News?","authors":"Claudia Orellana-Rodriguez, Derek Greene, Mark T. Keane","doi":"10.1561/106.00000009","DOIUrl":"https://doi.org/10.1561/106.00000009","url":null,"abstract":"Traditional news media face many serious concerns as their distribution channels are gradually being taken over by third parties (e.g., bloggers, citizen journalists, and news aggregators).  If traditional media is to remain competitive, it needs to develop innovative strategies around these channels, to maximize audience engagement with the news it provides.  In this paper, we focus on the issue of developing one such strategy for spreading news on Twitter. Using tweet corpora from two national news ecosystems -- 1.7M tweets from 200 journalists in Ireland and 1.2M tweets from 364 journalists in the UK --  and audience responses to these tweets, we develop predictive models to identify the features of journalists and news tweets that impact audience attention. These analyses reveal that different combinations of features influence audience engagement differentially from one news category to the next (e.g., sport versus business). Using these findings, we suggest a set of guidelines for journalists, designed to help them maximize engagement with the news they tweet. Finally, we discuss how such analyses can inform innovative dissemination strategies in digital media.","PeriodicalId":405637,"journal":{"name":"J. Web Sci.","volume":"59 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127681665","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":"It's All About Information? The Following Behaviour of Professors and PhD Students in Computer Science on Twitter","authors":"S. Linek, Asmelash Teka Hadgu, C. Hoffmann, R. Jäschke, C. Puschmann","doi":"10.1561/106.00000008","DOIUrl":"https://doi.org/10.1561/106.00000008","url":null,"abstract":"It’s All About Information? The Following Behaviour of Professors and PhD Students in Computer Science on Twitter","PeriodicalId":405637,"journal":{"name":"J. Web Sci.","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-06-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130171753","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":"Improving Collaborative Filtering Using a Cognitive Model of Human Category Learning","authors":"Simone Kopeinik, Dominik Kowald, Ilire Hasani-Mavriqi, E. Lex","doi":"10.1561/106.00000007","DOIUrl":"https://doi.org/10.1561/106.00000007","url":null,"abstract":"Classic resource recommenders like Collaborative Filtering treat users as being just another entity, thereby neglecting non-linear user-resource dynamics that shape attention and interpretation. SUSTAIN, as an unsupervised human category learning model, captures these dynamics. It aims to mimic a learner’s behavior of categorization. In this paper, we use three social bookmarking datasets gathered from BibSonomy, CiteULike and Delicious to investigate SUSTAIN as a user modeling approach to re-rank and enrich Collaborative Filtering following a hybrid recommender strategy. Evaluations against baseline algorithms in terms of recommender accuracy and computational complexity reveal encouraging results. Our approach substantially improves Collaborative Filtering and, depending on the dataset, successfully competes with a computationally much more expensive Matrix Factorization variant. In a further step, we explore SUSTAIN’s dynamics in our specific learning task and show that both, memorization of a user’s history and clus- tering, contribute to the algorithm’s performance. Finally, we observe that the users’ attentional foci determined by SUSTAIN correlate with the users’ level of curiosity, identified by the SPEAR algorithm. Overall, the results of our study show that SUSTAIN can be used to efficiently model attention-interpretation dynamics of users and can help to improve Collaborative Filtering in resource recommendation tasks.","PeriodicalId":405637,"journal":{"name":"J. Web Sci.","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-01-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124641006","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":"On the Ubiquity of Web Tracking: Insights from a Billion-Page Web Crawl","authors":"Sebastian Schelter, Jérôme Kunegis","doi":"10.1561/106.00000014","DOIUrl":"https://doi.org/10.1561/106.00000014","url":null,"abstract":"We perform a large-scale analysis of third-party trackers on the World Wide Web. We extract third-party embeddings from more than 3.5~billion web pages of the CommonCrawl 2012 corpus, and aggregate those to a dataset containing more than 140 million third-party embeddings in over 41 million domains. To the best of our knowledge, this constitutes the largest empirical web tracking dataset collected so far, and exceeds related studies by more than an order of magnitude in the number of  domains and web pages analyzed. Due to the enormous size of the dataset, we are able to perform a large-scale study of online tracking, on three levels: (1) On a global level, we give a precise figure for the extent of tracking, give insights into the structural properties of the `online tracking sphere' and analyse which trackers (and subsequently, which companies) are used by how many websites. (2) On a country-specific level, we analyse which trackers are used by websites in different countries, and identify the countries in which websites choose significantly different trackers than in the rest of the world. (3) We answer the question whether the content of websites influences the choice of trackers they use, leveraging more than ninety thousand categorized domains. In particular, we analyse whether highly privacy-critical websites about health and addiction make different choices of trackers than other websites. Based on the performed analyses, we confirm that trackers are widespread (as expected), and that a small number of trackers dominates the web (Google, Facebook and Twitter).  In particular, the three tracking domains with the highest PageRank are all owned by Google.  The only exception to this pattern are a few countries such as China and Russia. Our results suggest that this dominance is strongly associated with country-specific political factors such as freedom of the press. Furthermore, our data confirms that Google still operates services on Chinese websites, despite its proclaimed retreat from the Chinese market. We also confirm that websites with highly privacy-critical content are less likely to contain trackers (60% vs 90% for other websites), even though the majority of them still do contain trackers.","PeriodicalId":405637,"journal":{"name":"J. Web Sci.","volume":"350 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-07-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124361901","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":"Overlap in the Web Search Results of Google and Bing","authors":"R. Agrawal, Behzad Golshan, E. Papalexakis","doi":"10.1561/106.00000005","DOIUrl":"https://doi.org/10.1561/106.00000005","url":null,"abstract":"Google and Bing have emerged as the diarchy that arbitrates what documents are seen by Web searchers, particularly those desiring English language documents. We seek to study how distinctive are the top results presented to the users by the two search engines. A recent eye-tracking has shown that the web searchers decide whether to look at a document primarily based on the snippet and secondarily on the title of the document on the web search result page, and rarely based on the URL of the document. Given that the snippet and title generated by different search engines for the same document are often syntactically different, we first develop tools appropriate for conducting this study. Our empirical evaluation using these tools shows a surprising agreement in the results produced by the two engines for a wide variety of queries used in our study. Thus, this study raises the open question whether it is feasible to design a search engine that would produce results distinct from those produced by Google and Bing that the users will find helpful.","PeriodicalId":405637,"journal":{"name":"J. Web Sci.","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-05-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126622124","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}