@inproceedings{Butt_2015,
  added-at = {2020-09-28T10:24:20.000+0200},
  author = {Butt, Anila Sahar and Haller, Armin and Xie, Lexing},
  biburl = {https://www.bibsonomy.org/bibtex/23a702fef6f72dc145f022c0fafa72b68/parismic},
  booktitle = {Proceedings of the Knowledge Capture Conference on {ZZZ} - K-{CAP} 2015},
  description = {2815833.2815846},
  doi = {10.1145/2815833.2815846},
  interhash = {7ca3b71b8a0be3aedb9a614f8ab9947a},
  intrahash = {3a702fef6f72dc145f022c0fafa72b68},
  keywords = {data retrieval structure taxonomy web},
  publisher = {{ACM} Press},
  timestamp = {2020-09-28T10:24:20.000+0200},
  title = {A Taxonomy of Semantic Web Data Retrieval Techniques},
  url = {https://doi.org/10.1145%2F2815833.2815846},
  year = 2015
}

@article{jagli2016survey,
  abstract = {The most important need for a web based survey technology is speedy performance and accurate results
.Though there are variety of ways a survey can be taken manually and have it assessed manually but here we are introducing the survey site concept where the assessment of the survey responses are created automatically by applying certain statistics. In this paper we propose the idea of automated approach to the analysis of the survey where the results would be evident graphically to take a wise decision. Additional to graphical view we aim on forming a platform to view complex, tedious data in simple, understandable, interactive and visualized form},
  added-at = {2020-09-08T14:48:53.000+0200},
  author = {Jagli, Mrs. Dhanamma},
  biburl = {https://www.bibsonomy.org/bibtex/2e205264e4fec78b50977c3fb9087854b/janakirob},
  doi = {10.5121/acii.2016.3302},
  interhash = {9665738decd29efc94f3349dfb160759},
  intrahash = {e205264e4fec78b50977c3fb9087854b},
  journal = {Advanced Computational Intelligence: An International Journal (ACII)},
  keywords = {Analysis Architecture Based Data Mining Real Survey. Three Tier Time Web},
  month = {July},
  number = 3,
  pages = {09 - 15},
  timestamp = {2020-09-08T14:48:53.000+0200},
  title = {Survey Surfer : A Web Based Data Gathering and Analysis Application},
  url = {http://airccse.org/journal/acii/vol3.html},
  volume = 3,
  year = 2016
}

@article{noauthororeditor,
  abstract = {Hypertext Preprocessor PHP and Hypertext Markup Language HTML were important as scripting languages in most of the web based development. As an open source type, it has benefited educators and web developers in either education or commercial context due to their easy accessibility. However, there were many concepts and mechanisms that could be learnt and explored in order to produce quality system design in this respective language. As web based system transmit and exchange data within a vast network of Commercial Interconnected Network Internet , the data were exposed to many attackers who wish to steal the data, therefore the security aspect which focusing on protecting the data technically automated computation should be taken into account when designing the system, apart from the policies, rules or laws enforcement in cyber security environment. In this experiment, a light data manipulation technique were developed to convert the string user input into different forms of text representation of numerical value. Danial Kafi Ahmad | Zul Hilmi Abdullah | Siti Nuraini Ahmad "Data Security: String Manipulation by Random Value in Hypertext Preprocessor" Published in International Journal of Trend in Scientific Research and Development (ijtsrd), ISSN: 2456-6470, Volume-4 | Issue-4 , June 2020, URL: https://www.ijtsrd.com/papers/ijtsrd31283.pdf Paper Url :https://www.ijtsrd.com/computer-science/computer-security/31283/data-security-string-manipulation-by-random-value-in-hypertext-preprocessor/danial-kafi-ahmad
},
  added-at = {2020-07-16T11:06:23.000+0200},
  author = {Ahmad, Danial Kafi Ahmad | Zul Hilmi Abdullah | Siti Nuraini},
  biburl = {https://www.bibsonomy.org/bibtex/2a0728c75f04ba90d692c576907cf5d1a/ijtsrd},
  interhash = {3078643ba9fb38c4d624954ceb147010},
  intrahash = {a0728c75f04ba90d692c576907cf5d1a},
  issn = {2456-6470},
  journal = {International Journal of Trend in Scientific Research and Development},
  keywords = {Computers Data Iteration Manipulation Random Security Web},
  language = {English},
  month = {june},
  number = 4,
  pages = {873-878},
  timestamp = {2020-07-16T11:06:23.000+0200},
  title = {Data Security String Manipulation by Random Value in Hypertext Preprocessor
},
  url = {https://www.ijtsrd.com/computer-science/computer-security/31283/data-security-string-manipulation-by-random-value-in-hypertext-preprocessor/danial-kafi-ahmad},
  volume = 4,
  year = 2020
}

@techreport{hennig2018verbundprojekt,
  added-at = {2020-05-13T09:56:02.000+0200},
  address = {Kaiserslautern},
  author = {Hennig, Leonhard and Hemsen, Holmer and Schmeier, Sven and Uszkoreit, Hans and Markl, Volker and Siewert, Daniel and Bunk, Patrick and Tiedt, Philipp and Trömel, Marc and Gupta, Pankaj and Andrassy, Bernt and Müller, Kay and Frey, Johannes and Hellmann, Sebastian and Kilias, Torsten and Arnold, Sebastian and Löser, Alexander and Sauer, Petra and Technologies, Ubermetrics},
  biburl = {https://www.bibsonomy.org/bibtex/2b986ddb9c6d33a051f3fe55a7c26c7c5/mho},
  booktitle = {Verbundprojekt: Smart Data Web : zusammenfassender Abschlussbericht : Vorhaben: Verbundprojekt SDW Smart Data Web},
  description = {Verbundprojekt Smart Data Web zusammenfassender Abschlussbericht - Technische Informationsbibliothek (TIB)},
  interhash = {51ca9a1ee45d8c14f42f43b91e5c50bf},
  intrahash = {b986ddb9c6d33a051f3fe55a7c26c7c5},
  keywords = {Data Datenanalyse Datensammlung Science Semantic Web Wissensorganisation},
  month = {5},
  publisher = {Deutsches Forschungszentrum für Künstliche Intelligenz GmbH},
  timestamp = {2021-04-19T09:11:35.000+0200},
  title = {<i>Verbundprojekt: Smart Data Web : zusammenfassender Abschlussbericht : Vorhaben: Verbundprojekt SDW Smart Data Web</i>},
  url = {https://www.tib.eu/de/suchen/id/TIBKAT%3A1686069537/Verbundprojekt-Smart-Data-Web-zusammenfassender/},
  year = {submitted}
}

@article{Harth2010:Visnav,
  added-at = {2020-05-05T14:37:48.000+0200},
  author = {Harth, Andreas},
  bdsk-url-1 = {http://www.sciencedirect.com/science/article/pii/S1570826810000600},
  bdsk-url-2 = {http://dx.doi.org/10.1016/j.websem.2010.08.001},
  biburl = {https://www.bibsonomy.org/bibtex/27bf3635136dd16bd4c8c1fa8665b3c07/dice-research},
  doi = {10.1016/j.websem.2010.08.001},
  interhash = {761bf01626aba910d7c5250d9830b54e},
  intrahash = {7bf3635136dd16bd4c8c1fa8665b3c07},
  issn = {1570-8268},
  journal = {Web Semantics: Science, Services and Agents on the World Wide Web},
  keywords = {Web data},
  note = {Semantic Web Challenge 2009 User Interaction in Semantic Web research},
  number = 4,
  pages = {348--354},
  timestamp = {2023-04-25T16:33:57.000+0200},
  title = {{VisiNav}: A system for visual search and navigation on web data},
  url = {http://www.sciencedirect.com/science/article/pii/S1570826810000600},
  volume = 8,
  year = 2010
}

@article{noauthororeditor,
  abstract = {The Competition between different Web Service Providers to enhance their services and to increase the users' usage of their provided services raises the idea of our research. Our research is focusing on increasing the number of services that User or Developer will use. We proposed a web service’s recommendation model by applying the data mining techniques like Apriori algorithm to suggest another web service beside the one he got from the discovery process based on the user’s History. For implementing our model, we used a curated source for web services and users, which also contains a complete information about users and their web services usage. We found a BioCatalogue: our proposed
model was tested on a Curated Web Service Registry (BioCatalogue).and 70 % of users chose services from services that recommended by our model besides the discovered ones by BioCatalogue.},
  added-at = {2020-01-24T07:34:22.000+0100},
  author = {Prof.Dr.TorkeyI.Sultan and Khedr, Dr. Ayman E. and Alsheref, Fahad Kamal},
  biburl = {https://www.bibsonomy.org/bibtex/256affab885505e2ce497a2105c29d558/ijwsc},
  doi = {10.5121/ijwsc.2013.4403},
  interhash = {38d851c49b10c3c6d476fdb5fb13a9ba},
  intrahash = {56affab885505e2ce497a2105c29d558},
  issn = {0976 - 9811 (Online) ; 2230 - 7702 (print)},
  journal = {International Journal on Web Service Computing (IJWSC)},
  keywords = {BioCatalogue Data Mining Recommendation System Web and discovery services},
  language = {English},
  month = {December},
  number = 4,
  pages = {21-33},
  timestamp = {2020-01-24T07:34:22.000+0100},
  title = {ADAPTIVE MODEL FOR WEB SERVICE RECOMMENDATION},
  url = {http://airccse.org/journal/jwsc/papers/4413ijwsc03.pdf},
  volume = 4,
  year = 2013
}

@article{noauthororeditor,
  abstract = {A real world challenging task of the web master of an organization is to match the needs of user and keep their attention in their web site. So, only option is to capture the intuition of the user and provide them with the recommendation list. Most specifically, an online navigation behavior grows with each passing day, thus extracting information intelligently from it is a difficult issue. Web master should use web usage mining method to capture intuition. A WUM is designed to operate on web server logs which contain user’s navigation. Hence, recommendation system using WUM can be used to forecast the navigation pattern of user and recommend those to user in a form of recommendation list. In this paper, we propose a two tier architecture for capturing users intuition in the form of recommendation list containing pages visited by user and pages visited by other user’s having similar usage profile. The practical implementation of proposed architecture and algorithm shows that accuracy of user intuition capturing is improved.},
  added-at = {2019-12-27T07:14:58.000+0100},
  author = {Dixit, Dipa and Gadge, Jayant},
  biburl = {https://www.bibsonomy.org/bibtex/206f029680e7b260bbabfeb7f82fc2956/ijmit_journal},
  doi = {10.5121/ijmit.2010.2303},
  interhash = {d19270de09426c19e0e2af0d978f8c78},
  intrahash = {06f029680e7b260bbabfeb7f82fc2956},
  issn = {ISSN: 0975-5586 (Online); 0975-5926 (Print)},
  journal = {International Journal of Managing Information Technology (IJMIT)},
  keywords = {Classification Clustering Data Intelligence Mining Personalization Usage Web mining},
  language = {English},
  month = {August},
  number = 3,
  pages = {33 to 42},
  timestamp = {2019-12-27T07:14:58.000+0100},
  title = {Automatic Recommendation for Online Users Using Web Usage Mining
},
  url = {http://airccse.org/journal/ijmit/papers/0810ijmit03.pdf},
  volume = 2,
  year = 2010
}

@article{noauthororeditor,
  abstract = {Documents created and distributed on the Internet are ever changing in various forms. Most of existing works are devoted to topic modeling and the evolution of individual topics, while sequential relations of topics in successive documents published by a specific user are ignored. In order to characterize and detect personalized and abnormal behaviours of Internet users, we propose Sequential Topic Patterns STPs and formulate the problem of mining User aware Rare Sequential Topic Patterns URSTPs in document streams on the Internet. They are rare on the whole but relatively frequent for specific users, so can be applied in many real life scenarios, such as real time monitoring on abnormal user behaviours. Here present solutions to solve this innovative mining problem through three phases pre processing to extract probabilistic topics and identify sessions for different users, generating all the STP candidates with expected support values for each user by pattern growth, and selecting URSTPs by making useraware rarity analysis on derived STPs. Experiments on both real Twitter and synthetic datasets show that our approach can indeed discover special users and interpretable URSTPs effectively and efficiently, which significantly reflect users' characteristics. Rajeshri R. Shelke ""Identification of User Aware Rare Sequential Pattern in Document Stream- An Overview"" Published in International Journal of Trend in Scientific Research and Development (ijtsrd), ISSN: 2456-6470, Volume-3 | Issue-4 , June 2019, 

URL: https://www.ijtsrd.com/papers/ijtsrd24008.pdf

Paper URL: https://www.ijtsrd.com/computer-science/data-miining/24008/identification-of-user-aware-rare-sequential-pattern-in-document-stream--an-overview/rajeshri-r-shelke
},
  added-at = {2019-07-06T14:22:25.000+0200},
  author = {Shelke, Rajeshri R.},
  biburl = {https://www.bibsonomy.org/bibtex/27f4d0ec1d38c4233e0f607f9bf22d331/ijtsrd},
  doi = {https://doi.org/10.31142/ijtsrd24008},
  interhash = {df79634e3fe8b9780c193b20905ab779},
  intrahash = {7f4d0ec1d38c4233e0f607f9bf22d331},
  issn = {2456-6470},
  journal = {International Journal of Trend in Scientific Research and Development},
  keywords = {Data Miining Web document events mining pattern-growth. patterns rare sequential streams},
  language = {English},
  month = {june},
  number = 4,
  pages = {1340-1342},
  timestamp = {2019-07-06T14:22:25.000+0200},
  title = {Identification of User Aware Rare Sequential Pattern in Document Stream An Overview
},
  url = {https://www.ijtsrd.com/computer-science/data-miining/24008/identification-of-user-aware-rare-sequential-pattern-in-document-stream--an-overview/rajeshri-r-shelke},
  volume = 3,
  year = 2019
}

@article{noauthororeditor,
  abstract = {A Data-Warehouse is a repository that fetches data from many diverse sources within an organization for Business-Reporting and Business-Analysis. The reports created from intricate queries within a Data-Warehouse are used to improve business process, make optimal judgements, and even announce viable advantages. Since the Organizational Data is increasing exponentially day by day hence in-house Data warehouse is getting obsolete and a new concept of Cloud Based Data Warehouse is emerging. The leading player in this cloud based Data-Warehouse is AWS Redshift. After the data is collated inside the Data-Warehouse, the next step is to retrieve some analytical data and use it to boost business acumen and subsequently increase business revenue and efficiency. The above business analytics can be performed using various tools. The market leader in this regard is Microsoft Power BI. In this paper, we will try to analyze the working of Microsoft Power BI in coordination with AWS Redshift. Prashant Dutta "Business Analytics using Microsoft Power BI and AWS Redshift" Published in International Journal of Trend in Scientific Research and Development (ijtsrd), ISSN: 2456-6470, Volume-3 | Issue-2 , February 2019, URL: https://www.ijtsrd.com/papers/ijtsrd21545.pdf
},
  added-at = {2019-05-29T10:06:02.000+0200},
  author = {Dutta, Prashant},
  biburl = {https://www.bibsonomy.org/bibtex/2a0403d226d0f4ded05e44fb876ea349b/ijtsrd},
  doi = {https://doi.org/10.31142/ijtsrd21545},
  interhash = {5ccbf20700d4a63dfda8fba5bac256c8},
  intrahash = {a0403d226d0f4ded05e44fb876ea349b},
  issn = {2456-6470},
  journal = {International Journal of Trend in Scientific Research and Development},
  keywords = {AWS Amazon BI Data Power Redshift Service Warehouse Web},
  language = {English},
  month = feb,
  number = 2,
  pages = {984-986},
  timestamp = {2019-05-29T10:06:02.000+0200},
  title = {Business Analytics using Microsoft Power BI and AWS Redshift
},
  url = {https://www.ijtsrd.com/engineering/computer-engineering/21545/business-analytics-using-microsoft-power-bi-and-aws-redshift/prashant-dutta},
  volume = 3,
  year = 2019
}

@misc{KAISBCS:15p,
  added-at = {2019-02-15T11:06:14.000+0100},
  author = {Kibanov, Mark and Atzmueller, Martin and Illig, Jens and Scholz, Christoph and Barrat, Alain and Cattuto, Ciro and Stumme, Gerd},
  biburl = {https://www.bibsonomy.org/bibtex/2eba4cf7c5221d117285c8395aa10fe73/stumme},
  howpublished = {Computational Social Science Winter Symposium 2015, Poster},
  interhash = {b070c1455e0d0b4aa51a9feac3724c65},
  intrahash = {eba4cf7c5221d117285c8395aa10fe73},
  keywords = {2015 analysis data face-to-face itegpub myown network offline online rfid social web},
  timestamp = {2019-02-15T11:06:14.000+0100},
  title = {{Is Web Content a Good Proxy for Real-Life Interaction? A Case Study Considering Online and Offline Interactions of Computer Scientists (Poster)}},
  url = {http://www.gesis.org/css-wintersymposium/program/poster-sessions-presentations/},
  year = 2015
}

@article{noauthororeditor,
  abstract = {The knowledge on the cobweb is growing expressively. Without a recommendation theory, the clients may come through lots of instance on the network in finding the knowledge they are stimulated in. Today, many web recommendation theories cannot give clients adequate symbolized help but provide the client with lots of immaterial knowledge. One of the main reasons is that it can't correctly extract user's interests. Therefore, analyzing users' Web Log Data and extracting users' potential interested domains become very important research topics of web usage mining. If users' interests can be automatically detected from users' Web Log Data, they can be used for information recommendation which will be useful for both the users and the Web site developers. In this paper, one novel algorithm is proposed to extract users' interests. The algorithm is based on visit time and visit density. The experimental results of the proposed method succeed in finding user's interested domains. K. Srinivasa Rao | Dr. A. Ramesh Babu | Dr. M. Krishna Murthy"Extracting the User's Interests from Web Log Data using A Time Based Algorithm" Published in International Journal of Trend in Scientific Research and Development (ijtsrd), ISSN: 2456-6470, Volume-1 | Issue-6 , October 2017, URL: http://www.ijtsrd.com/papers/ijtsrd2474.pdf  http://www.ijtsrd.com/computer-science/data-miining/2474/extracting-the-user's-interests-from-web-log-data-using-a-time-based-algorithm/k-srinivasa-rao
},
  added-at = {2018-09-11T07:15:00.000+0200},
  author = {Murthy, K. Srinivasa Rao Dr. A. Ramesh Babu Dr. M. Krishna},
  biburl = {https://www.bibsonomy.org/bibtex/2d55ac064fe720cf7e72cf647e5c48bc5/ijtsrd},
  interhash = {bb24c3d700c8cd933e9e3ed0b8bc4b73},
  intrahash = {d55ac064fe720cf7e72cf647e5c48bc5},
  issn = {2456-6470},
  journal = {International Journal of Trend in Scientific Research and Development},
  keywords = {Content Data Miining Mining Usage Web Weblog data},
  language = {English},
  month = oct,
  number = 6,
  pages = {477-482},
  timestamp = {2018-10-02T11:01:27.000+0200},
  title = {Extracting the User's Interests from Web Log Data using A Time Based Algorithm
},
  url = {http://www.ijtsrd.com/computer-science/data-miining/2474/extracting-the-user's-interests-from-web-log-data-using-a-time-based-algorithm/k-srinivasa-rao},
  volume = 1,
  year = 2017
}

@article{noauthororeditor,
  abstract = {Clustering an information is gathering an data together as indicated by their likeness. There are numerous clustering algorithms are availble here to cluster web logs. In this paper, it mainly focusing on clustering algorithm that is used for clustering web logs. Also this survey is about an algorithm which is used to cluster an web log or web usage data. Anandha Jothi | Gayathri. P"A Survey on: Clustering Algorithms in Web Usage Mining" Published in International Journal of Trend in Scientific Research and Development (ijtsrd), ISSN: 2456-6470, Volume-2 | Issue-4 , June 2018, URL: http://www.ijtsrd.com/papers/ijtsrd12742.pdf  http://www.ijtsrd.com/computer-science/other/12742/a-survey-on-clustering-algorithms-in-web-usage-mining/anandha-jothi
},
  added-at = {2018-09-05T14:21:30.000+0200},
  author = {P, Anandha Jothi Gayathri.},
  biburl = {https://www.bibsonomy.org/bibtex/254b8bda41c7f418f1863a98e4107dd76/ijtsrd},
  interhash = {f4d54c320ea1b95926c122dc033acdf4},
  intrahash = {54b8bda41c7f418f1863a98e4107dd76},
  issn = {2456-6470},
  journal = {International Journal of Trend in Scientific Research and Development},
  keywords = {Clustering algorithms data logs usage web},
  language = {English},
  month = {June},
  number = 4,
  pages = {249-251},
  timestamp = {2018-10-02T11:01:27.000+0200},
  title = {A Survey on: Clustering Algorithms in Web Usage Mining
},
  url = {http://www.ijtsrd.com/computer-science/other/12742/a-survey-on-clustering-algorithms-in-web-usage-mining/anandha-jothi},
  volume = 2,
  year = 2018
}

@article{noauthororeditor,
  abstract = {Many data owners are required to release variety of data in real world application it has vital importance of discovery valuable information stay behind the data. However existing we focus on the de- identification policy which is the common privacy preserving approach. By using de-identification policy a continues balance between privacy protection and data utility can be achieved by choosing the appropriate. We propose one parallel algorithm 'œSKY FILTER POLICY GENERATOR' that can be filtered the optimized data' web ranking algorithm' provide the user preferred data. Each user has their own privacy username and password, through the sky filter (data analytic operator) user willing data given to the user. Each user is identified by de identification policy. G. Sneka | H. Sharmila | R. Banumathi"De-Identification Technology Involves Web Mining" Published in International Journal of Trend in Scientific Research and Development (ijtsrd), ISSN: 2456-6470, Volume-2 | Issue-3 , April 2018, URL: http://www.ijtsrd.com/papers/ijtsrd11484.pdf  http://www.ijtsrd.com/engineering/computer-engineering/11484/de-identification-technology-involves-web-mining/g-sneka
},
  added-at = {2018-09-05T06:51:12.000+0200},
  author = {Banumathi, G. Sneka H. Sharmila R.},
  biburl = {https://www.bibsonomy.org/bibtex/21fd5a97eaed49ea75c0698da1518a349/ijtsrd},
  interhash = {7fa9ea1dd0322f04d0d851d97b7dd68d},
  intrahash = {1fd5a97eaed49ea75c0698da1518a349},
  issn = {2456-6470},
  journal = {International Journal of Trend in Scientific Research and Development},
  keywords = {Computer Engineering algorithm analytic data filter generator policy ranking sky web},
  language = {English},
  month = {April},
  number = 3,
  pages = {1502-1505},
  timestamp = {2018-10-02T11:01:27.000+0200},
  title = {De-Identification Technology Involves Web Mining
},
  url = {http://www.ijtsrd.com/engineering/computer-engineering/11484/de-identification-technology-involves-web-mining/g-sneka},
  volume = 2,
  year = 2018
}

@misc{KAISBCS:15p,
  added-at = {2018-08-30T11:58:32.000+0200},
  author = {Kibanov, Mark and Atzmueller, Martin and Illig, Jens and Scholz, Christoph and Barrat, Alain and Cattuto, Ciro and Stumme, Gerd},
  biburl = {https://www.bibsonomy.org/bibtex/2eba4cf7c5221d117285c8395aa10fe73/kde-alumni},
  howpublished = {Computational Social Science Winter Symposium 2015, Poster},
  interhash = {b070c1455e0d0b4aa51a9feac3724c65},
  intrahash = {eba4cf7c5221d117285c8395aa10fe73},
  keywords = {2015 analysis data face-to-face itegpub myown network offline online rfid social web},
  timestamp = {2018-08-30T11:58:32.000+0200},
  title = {{Is Web Content a Good Proxy for Real-Life Interaction? A Case Study Considering Online and Offline Interactions of Computer Scientists (Poster)}},
  url = {http://www.gesis.org/css-wintersymposium/program/poster-sessions-presentations/},
  year = 2015
}

@article{51seitenPaper,
  added-at = {2018-08-30T11:56:12.000+0200},
  author = {Mitzlaff, Folke and Atzmueller, Martin and Benz, Dominik and Hotho, Andreas and Stumme, Gerd},
  biburl = {https://www.bibsonomy.org/bibtex/2424d0f2d4a5c9a0eb68cbf2fc5b0010a/kde-alumni},
  interhash = {40aa075d925f2e6e009986fd9e60b11b},
  intrahash = {424d0f2d4a5c9a0eb68cbf2fc5b0010a},
  journal = {CoRR/abs},
  keywords = {2013 data itegpub mining myown social ubiquitous venus web},
  timestamp = {2018-08-30T11:56:12.000+0200},
  title = {{User-Relatedness and Community Structure in Social Interaction Networks}},
  volume = {1309.3888},
  year = 2013
}

@incollection{huurdeman2017collaborative,
  abstract = {In our times, researchers create and gather their datasets, irrevocably changing from solely “small” to increasingly “big” data. Institutions provide more and more services to manage, store and access this essential research data. However, despite the invaluable services provided by repositories, there is still a mismatch between the myriad of operations carried out by researchers, and the storage services offered by generalized repositories: often, only the end products of the research process are stored. This may mean that valuable operations and transformations of data during the research process are lost, in effect also making it harder for future researchers to interpret this data. To address this issue, and to bring researchers and institutions closer together, we propose a more collaborative approach, potentially involving researchers in their entire workflow, from data creation to use and potential reuse. This proposition is contextualized via the concrete use case of the web archive. Organizations and individuals across the globe archive web content, assembled into vast web archives. These web archives could potentially be used as research datasets in various settings, ranging from computer science to the humanities. However, they have scarcely been used for research thus far, due to a number of limitations, including suboptimal access services for research. This chapter discusses the experiences and lessons learned in the concrete case of the web archive, and their implications for research data management at large.},
  added-at = {2018-08-08T13:41:18.000+0200},
  address = {Berlin, Boston},
  author = {Huurdeman, Hugo C. and Kamps, Jaap},
  biburl = {https://www.bibsonomy.org/bibtex/22444e7c2942b28790d29b1dfadc78576/jaeschke},
  booktitle = {Research Data Management - A European Perspective},
  chapter = 4,
  doi = {10.1515/9783110365634-005},
  editor = {Kruse, Filip and Thestrup, Jesper Boserup},
  interhash = {63a8018cfd149257cd199034016cd538},
  intrahash = {2444e7c2942b28790d29b1dfadc78576},
  isbn = {9783110365634},
  keywords = {archive data management research web},
  pages = {55-78},
  publisher = {De Gruyter},
  timestamp = {2018-08-08T13:41:18.000+0200},
  title = {A Collaborative Approach to Research Data Management in a Web Archive Context},
  url = {https://www.degruyter.com/view/books/9783110365634/9783110365634-005/9783110365634-005.xml},
  year = 2017
}

@article{celli2015discovering,
  abstract = {The social media revolution is having a dramatic effect on the world of scientific publication. Scientists now publish their research interests, theories and outcomes across numerous channels, including personal blogs and other thematic web spaces where ideas, activities and partial results are discussed. Accordingly, information systems that facilitate access to scientific literature must learn to cope with this valuable and varied data, evolving to make this research easily discoverable and available to end users. In this paper we describe the incremental process of discovering web resources in the domain of agricultural science and technology. Making use of Linked Open Data methodologies, we interlink a wide array of custom-crawled resources with the AGRIS bibliographic database in order to enrich the user experience of the AGRIS website. We also discuss the SemaGrow Stack, a query federation and data integration infrastructure used to estimate the semantic distance between crawled web resources and AGRIS. },
  added-at = {2018-08-08T11:16:11.000+0200},
  author = {Celli, F and Keizer, J and Jaques, Y and Konstantopoulos, S and Vudragović, D},
  biburl = {https://www.bibsonomy.org/bibtex/21dbdfbc56bbbf92de114886f226ea986/jaeschke},
  description = {Discovering, Indexing and Interlinking Information Resources},
  doi = {10.12688/f1000research.6848.2},
  interhash = {86aea1c14e4ea4463557a49a0fa4479d},
  intrahash = {1dbdfbc56bbbf92de114886f226ea986},
  journal = {F1000Res},
  keywords = {bibliographic crawling data gaw lod research web},
  pages = {432-432},
  pmid = {26834982},
  timestamp = {2018-08-08T11:16:11.000+0200},
  title = {Discovering, Indexing and Interlinking Information Resources},
  url = {https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4722689/},
  volume = 4,
  year = 2015
}

@article{Serra2017,
  abstract = {{\textless}p{\textgreater}O artigo discorre sobre as possibilidades de aplica{\c{c}}{\~{a}}o de conceitos da web sem{\^{a}}ntica no cat{\'{a}}logo, por meio da aplica{\c{c}}{\~{a}}o de linked data, favorecendo a troca de informa{\c{c}}{\~{o}}es de forma din{\^{a}}mica, leg{\'{i}}vel por pessoas e m{\'{a}}quinas, com dados estruturados e conectados. Para tanto, trata-se de pesquisa explorat{\'{o}}ria realizada por meio de levantamento bibliogr{\'{a}}fico, com sele{\c{c}}{\~{a}}o de textos que discorrem sobre os cat{\'{a}}logos, partindo dos objetivos enunciados por Cutter at{\'{e}} a disponibiliza{\c{c}}{\~{a}}o dos mesmos na Web; e identifica{\c{c}}{\~{a}}o da web sem{\^{a}}ntica e linked data. O formato MARC {\'{e}} apresentado como elemento que iniciou a descri{\c{c}}{\~{a}}o em formato leg{\'{i}}vel por m{\'{a}}quinas e permitiu o interc{\^{a}}mbio de registros bibliogr{\'{a}}ficos, mostrando-se, contudo, incapaz de satisfazer as necessidades descritivas atuais. A web sem{\^{a}}ntica {\'{e}} apresentada, partindo dos componentes de metadados exemplificados por ferramentas e modelo de dados at{\'{e}} o linked data. O RDF {\'{e}} apresentado como um modelo de dados que permite a constru{\c{c}}{\~{a}}o da estrutura necess{\'{a}}ria para a liga{\c{c}}{\~{a}}o de dados na Web, proporcionando flexibilidade na escolha dos elementos descritivos que s{\~{a}}o utilizados com recursos bibliogr{\'{a}}ficos. Foram identificadas iniciativas de utiliza{\c{c}}{\~{a}}o de linked data em bibliotecas, como a estrutura{\c{c}}{\~{a}}o de vocabul{\'{a}}rios e nomes de pessoas, identificando resultados em seu emprego. O texto finaliza com a identifica{\c{c}}{\~{a}}o de ganhos oriundos do uso de linked data nos cat{\'{a}}logos das bibliotecas e a necessidade de publica{\c{c}}{\~{a}}o de dados abertos e interoper{\'{a}}veis pelas institui{\c{c}}{\~{o}}es, ampliando as possibilidades de novas liga{\c{c}}{\~{o}}es de dados.{\textless}/p{\textgreater}},
  added-at = {2018-06-06T10:57:26.000+0200},
  author = {Serra, Liliana Giusti and Segundo, Jos{\'{e}} Eduardo Santar{\'{e}}m},
  biburl = {https://www.bibsonomy.org/bibtex/2548dd9df524bf49f344dcaa2a65a71e5/merlo},
  doi = {10.19132/1808-5245232.167-185},
  interhash = {de2e79eff834175ee8f0b1af8affc4e7},
  intrahash = {548dd9df524bf49f344dcaa2a65a71e5},
  issn = {1808-5245},
  journal = {Em Quest{\~{a}}o},
  keywords = {Catalogue. Data Estrutura Linked Metadados. Metadata. Semantic Web bibliodocs dados. data. de sem{\^{a}}ntica. structure.,Cat{\'{a}}logo. web.},
  month = apr,
  number = 2,
  pages = 167,
  timestamp = {2018-06-06T10:58:21.000+0200},
  title = {{O cat{\'{a}}logo da biblioteca e o linked data}},
  url = {http://seer.ufrgs.br/index.php/EmQuestao/article/view/67162},
  volume = 23,
  year = 2017
}

@article{Srivastavaetal,
  added-at = {2018-04-30T23:03:04.000+0200},
  author = {Srivastava, J. and Cooley, R. and Deshpande, M. and Tan, P.-N.},
  biburl = {https://www.bibsonomy.org/bibtex/2dc941da0f5c7da937269241b0df0b3b3/daswesen},
  interhash = {08571943908ec1aa9aa5c003e79d5b8d},
  intrahash = {dc941da0f5c7da937269241b0df0b3b3},
  journal = {SIGKDD Explorations},
  keywords = {data discovery mining patterns usage web},
  number = 2,
  pages = {12--23},
  timestamp = {2018-04-30T23:03:04.000+0200},
  title = {Web usage mining: discovery and application of usage patterns from web data},
  url = {/brokenurl#citeseer.nj.nec.com/srivastava00web.html},
  volume = 1,
  year = 2000
}