Laura M. Koesten, Elena Demidova, V. Savenkov, J. Breslin, Óscar Corcho, S. Dietze, E. Simperl
{"title":"PROFILES & DATA: SEARCH International Workshop on Profiling and Searching Data on the Web Chairs' Welcome & Organization","authors":"Laura M. Koesten, Elena Demidova, V. Savenkov, J. Breslin, Óscar Corcho, S. Dietze, E. Simperl","doi":"10.1145/3184558.3192316","DOIUrl":"https://doi.org/10.1145/3184558.3192316","url":null,"abstract":"The web of data has seen tremendous growth recently. New forms of structured data have emerged in the form of web markup, such as schema.org and web tables. Exploiting these rich, heterogeneous and evolving data sources has become increasingly important for many different types of applications, including (federated) search, question answering and fact verification. The objective of the PROFILES & DATA:SEARCH Workshop is to bring together researchers and practitioners interested in the development of data search techniques, data profiling, and dataset retrieval on the web. This includes looking at the specifics of data-centric information seeking behaviours, understanding interaction challenges in data search on the web, and analysing the cognitive processes involved in the consumption of structured data by users. At the same time, we aim to discuss technologies addressing data search including semantics, information retrieval for web data (ranking algorithms and indexing), in particular in the context of decentralised and distributed systems, such as the web. We are interested in approaches to analyse, characterise and discover data sources. We want to facilitate a discussion around data search across formats and domain-specific applications. The PROFILES & DATA:SEARCH Workshop includes papers on a variety of topics such as profiling and data search, including querying and searching for structured data, profiling applications for cultural heritage, as well as data quality improvements through schema inference, content analysis and communities.","PeriodicalId":235572,"journal":{"name":"Companion Proceedings of the The Web Conference 2018","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-04-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114652200","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":"Detection of Strength and Causal Agents of Stress and Relaxation for Tweets","authors":"Reshmi Gopalakrishna Pillai","doi":"10.1145/3184558.3186572","DOIUrl":"https://doi.org/10.1145/3184558.3186572","url":null,"abstract":"The ability to detect human stress and relaxation is central for timely diagnosing stress-related diseases, ensuring customer satisfaction in services and managing human-centric applications such as traffic management. Traditional methods employ stress measuring scales or physiological monitoring which may be intrusive and inconvenient. Instead, the ubiquitous nature of social media can be leveraged to identify stress and relaxation. In this PhD research, we introduce an improved method to detect expressions of stress and relaxation in social media content. It uses word sense vectors for word sense disambiguation to improve the performance of the first ever lexicon-based stress/relaxation detection algorithm TensiStrength. Experimental results show that TensiStrength with word sense disambiguation performs better than the original TensiStrength and state-of-the-art machine learning methods in terms of Pearson's correlation and accuracy. We also suggest a novel, word-vector based approach for detecting causes of stress and relaxation in social media content.","PeriodicalId":235572,"journal":{"name":"Companion Proceedings of the The Web Conference 2018","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-04-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117151298","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":"Investigating Similarity of Nodes' Attributes in Topological Based Communities.","authors":"Rajesh Sharma, D. Montesi","doi":"10.1145/3184558.3191564","DOIUrl":"https://doi.org/10.1145/3184558.3191564","url":null,"abstract":"One of the important problems in the domain of network science is the community detection. In the past, various topological based community detection algorithms have been proposed. Recently, researchers have taken into account at- tributes of the nodes while proposing community detection algorithms. In this work, we investigate if the nodes in a community, identified through topology based algorithms al- so exhibit attribute similarity. Using four different kinds of similarity metrics, we analyse the attribute similarity of the nodes within the communities derived using five different types of topological based community detection algorithms. Based on our analysis of three real social network datasets, we found on an average of 50% attribute similarity among the nodes in the communities.","PeriodicalId":235572,"journal":{"name":"Companion Proceedings of the The Web Conference 2018","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-04-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121136824","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}
Gaurav Bhatt, Aman Sharma, Shivam Sharma, Ankush Nagpal, B. Raman, A. Mittal
{"title":"Combining Neural, Statistical and External Features for Fake News Stance Identification","authors":"Gaurav Bhatt, Aman Sharma, Shivam Sharma, Ankush Nagpal, B. Raman, A. Mittal","doi":"10.1145/3184558.3191577","DOIUrl":"https://doi.org/10.1145/3184558.3191577","url":null,"abstract":"Identifying the veracity of a news article is an interesting problem while automating this process can be a challenging task. Detection of a news article as fake is still an open question as it is contingent on many factors which the current state-of-the-art models fail to incorporate. In this paper, we explore a subtask to fake news identification, and that is stance detection. Given a news article, the task is to determine the relevance of the body and its claim. We present a novel idea that combines the neural, statistical and external features to provide an efficient solution to this problem. We compute the neural embedding from the deep recurrent model, statistical features from the weighted n-gram bag-of-words model and handcrafted external features with the help of feature engineering heuristics. Finally, using deep neural layer all the features are combined, thereby classifying the headline-body news pair as agree, disagree, discuss, or unrelated. Through extensive experiments, we find that the proposed model outperforms all the state-of-the-art techniques including the submissions to the fake news challenge.","PeriodicalId":235572,"journal":{"name":"Companion Proceedings of the The Web Conference 2018","volume":"72 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-04-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127361484","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}
Daniel Alexandrov, Viktor Karepin, Ilya Musabirov, D. Chuprina
{"title":"Educational Migration from Russia to the Nordic Countries, China and the Middle East. Social Media Data","authors":"Daniel Alexandrov, Viktor Karepin, Ilya Musabirov, D. Chuprina","doi":"10.1145/3184558.3186923","DOIUrl":"https://doi.org/10.1145/3184558.3186923","url":null,"abstract":"We use social media and WWW data to analyse international educational migration from Russia. We find substantial regional differences in migration patterns for three contrast directions: the Nordic countries, China and the Middle East. We built a model of migration flows with geographic distances to destination countries, various socio-demographic data and institutional characteristics of educational organisations.","PeriodicalId":235572,"journal":{"name":"Companion Proceedings of the The Web Conference 2018","volume":"15 4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-04-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123452993","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":"An Improved Sampler for Bayesian Personalized Ranking by Leveraging View Data","authors":"Jingtao Ding, Fuli Feng, Xiangnan He, Guanghui Yu, Yong Li, Depeng Jin","doi":"10.1145/3184558.3186905","DOIUrl":"https://doi.org/10.1145/3184558.3186905","url":null,"abstract":"Bayesian Personalized Ranking (BPR) is a representative pairwise learning method for optimizing recommendation models. It is widely known that the performance of BPR depends largely on the quality of the negative sampler. In this short paper, we make two contributions with respect to BPR. First, we find that sampling negative items from the whole space is unnecessary and may even degrade the performance. Second, focusing on the purchase feedback of the E-commerce domain, we propose a simple yet effective sampler for BPR by leveraging the additional view data. Compared to the vanilla BPR that applies a uniform sampler on all candidates, our view-aware sampler enhances BPR with a relative improvement of 27.36% and 69.54% on two real-world datasets respectively.","PeriodicalId":235572,"journal":{"name":"Companion Proceedings of the The Web Conference 2018","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-04-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125356974","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":"Demo Track Chairs' Welcome & Organization","authors":"Paul T. Groth, A. Gyrard","doi":"10.1145/3184558.3192297","DOIUrl":"https://doi.org/10.1145/3184558.3192297","url":null,"abstract":"The Demo Track is one of the most exciting parts of any Web Conference. It allows researchers and practitioners to demonstrate new systems in an engaging and hands-on manner to the community. The Web has been driven forward by building systems and technology. The demo track is a venue that encourages this sort of important type of result This year the track received 71 submissions of those 30 were accepted for a 42% accept rate. We had a comprehensive review procedure that looked at a number of dimensions including the novelty of the demo, its fit with the conference, its research content, and its potential for audience engagement. We were pleased by the number of submissions that included links to online demonstrations and/or videos. This gave reviewers additional information about how the demo would be presented. Overall, we had 232 reviews across all submissions. Many of the reviews provided not only a their expert judgement but ways in which the submissions could be improved. It is often difficult judging demonstrations as there are multiple factors to be taken into account. We want to thank the entire committee for taking the time to support the track. The resulting set of selected demos reflects the wide-variety of technology and research interests impacting the wide. Demonstrations cover topics such as using data on the web, the integration of the web and the physical world, knowledge graphs, search engines, security and privacy, and dealing with multimedia data. We believe that these demos provide an exciting taste of the future of the Web.","PeriodicalId":235572,"journal":{"name":"Companion Proceedings of the The Web Conference 2018","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-04-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125521226","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":"The BIG Web Track Chairs' Welcome & Organization","authors":"E. Gabrilovich, Kira Radinsky, Kuansan Wang","doi":"10.1145/3184558.3192292","DOIUrl":"https://doi.org/10.1145/3184558.3192292","url":null,"abstract":"It is our great pleasure to welcome you to the BIG Web Track of the Web Conference 2018. Many of today's most successful enterprises in business and in science are built on the collection and analysis of data. The sheer volume and richness of these data sets has stimulated a massive wave of innovation. In addition, this revolution has also sparked important debate on data privacy policies, ethics, and governance. This track started as a co-located event called BigData Innovators Gathering (BIG) with a vision to bring together academic and industry leaders in the Big Data space to share the state of the art and its successful applications in business. This event will be co-located with the Web conference for the fifth time, but now as a fully fledged alternate track named The BIG Web in The Web Conference 2018 in Lyon. This year's track consists of two keynotes, a panel on machine learning in the field of medicine, and 11 invited talks. In addition, we have accepted 6 papers from 35 submissions (with an acceptance ratio of 17%).","PeriodicalId":235572,"journal":{"name":"Companion Proceedings of the The Web Conference 2018","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-04-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126865658","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":"An Empirical Study of the Framework Impact on the Security of JavaScript Web Applications","authors":"Ksenia Peguero, N. Zhang, Xiuzhen Cheng","doi":"10.1145/3184558.3188736","DOIUrl":"https://doi.org/10.1145/3184558.3188736","url":null,"abstract":"textitBackground: JavaScript frameworks are widely used to create client-side and server-side parts of contemporary web applications. Vulnerabilities like cross-site scripting introduce significant risks in web applications. textitAim: The goal of our study is to understand how the security features of a framework impact the security of the applications written using that framework. textitMethod: In this paper, we present four locations in an application, relative to the framework being used, where a mitigation can be applied. We perform an empirical study of JavaScript applications that use the three most common template engines: Jade/Pug, EJS, and Angular. Using automated and manual analysis of each group of applications, we identify the number of projects vulnerable to cross-site scripting, and the number of vulnerabilities in each project, based on the framework used. textitResults: We analyze the results to compare the number of vulnerable projects to the mitigation locations used in each framework and perform statistical analysis of confounding variables. textitConclusions: The location of the mitigation impacts the application's security posture, with mitigations placed within the framework resulting in more secure applications.","PeriodicalId":235572,"journal":{"name":"Companion Proceedings of the The Web Conference 2018","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-04-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115580666","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":"Post Purchase Search Engine Marketing","authors":"Qianyun Zhang, Shawndra Hill, David M. Rothschild","doi":"10.1145/3184558.3186583","DOIUrl":"https://doi.org/10.1145/3184558.3186583","url":null,"abstract":"Although consumer behavior in response to search engine marketing has been studied extensively, few efforts have been made to understand how consumers search and respond to ads post purchase. Advertising to existing customers the same way as to prospective customers inevitably leads to wasteful and inefficient marketing. Employing a unique dataset that combines both search query and purchase data, we examine consumers' searching behavior and response to search engine marketing after purchase. We study large advertising campaigns for two popular technology products. We find that over half of the branded keyword searches come from consumers who already purchased the products, and that advertising response varies based on whether searchers are pre- or post-purchase. In general, post-purchase searchers are less likely to click on focal brand ads (i.e., they are less responsive to ads for products they already own). However, post-purchase searchers are still responsive to advertising and much more likely to click on ads for complementary products (i.e., they are more responsive to ads for relevant products other than the focal product).","PeriodicalId":235572,"journal":{"name":"Companion Proceedings of the The Web Conference 2018","volume":"202 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-04-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122373053","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}