@article{Hoonlor:2013:TCS:2507771.2500892, abstract = {Keywords in the ACM Digital Library and IEEE Xplore digital library and in NSF grants anticipate future CS research.}, acmid = {2500892}, address = {New York, NY, USA}, author = {Hoonlor, Apirak and Szymanski, Boleslaw K. and Zaki, Mohammed J.}, doi = {10.1145/2500892}, interhash = {425133ebceab2bce5f418ffd9917df55}, intrahash = {4a2aee492bfcfcdbbcc7774bdcddd4a2}, issn = {0001-0782}, issue_date = {October 2013}, journal = {Commun. ACM}, month = oct, number = 10, numpages = {10}, pages = {74--83}, publisher = {ACM}, title = {Trends in Computer Science Research}, url = {http://doi.acm.org/10.1145/2500892}, volume = 56, year = 2013 } @article{cho2006stanford, abstract = {We describe the design and performance of WebBase, a tool for Web research. The system includes a highly customizable crawler, a repository for collected Web pages, an indexer for both text and link-related page features, and a high-speed content distribution facility. The distribution module enables researchers world-wide to retrieve pages from WebBase, and stream them across the Internet at high speed. The advantage for the researchers is that they need not all crawl the Web before beginning their research. WebBase has been used by scores of research and teaching organizations world-wide, mostly for investigations into Web topology and linguistic content analysis. After describing the system's architecture, we explain our engineering decisions for each of the WebBase components, and present respective performance measurements.}, acmid = {1149124}, address = {New York, NY, USA}, author = {Cho, Junghoo and Garcia-Molina, Hector and Haveliwala, Taher and Lam, Wang and Paepcke, Andreas and Raghavan, Sriram and Wesley, Gary}, doi = {10.1145/1149121.1149124}, interhash = {bebbc072ea2dccf4c2b27abf244c1f08}, intrahash = {3cd21bf8a87619e0489b8da177c9f0b4}, issn = {1533-5399}, issue_date = {May 2006}, journal = {ACM Transactions on Internet Technology}, month = may, number = 2, numpages = {34}, pages = {153--186}, publisher = {ACM}, title = {Stanford WebBase components and applications}, url = {http://doi.acm.org/10.1145/1149121.1149124}, volume = 6, year = 2006 } @article{stirling2012archives, abstract = {The Internet has been covered by legal deposit legislation in France since 2006, making web archiving one of the missions of the Bibliothèque nationale de France (BnF). Access to the web archives has been provided in the library on an experimental basis since 2008. In the context of increasing interest in many countries in web archiving and how it may best serve the needs of researchers, especially in the expanding field of Internet studies for social sciences, a qualitative study was performed, based on interviews with potential users of the web archives held at the BnF, and particularly researchers working in various areas related to the Internet. The study aimed to explore their needs in terms of both content and services, and also to analyse different ways of representing the archives, in order to identify ways of increasing their use. While the interest of maintaining the "memory" of the web is obvious to the researchers, they are faced with the difficulty of defining, in what is a seemingly limitless space, meaningful collections of documents. Cultural heritage institutions such as national libraries are perceived as trusted third parties capable of creating rationally-constructed and well-documented collections, but such archives raise certain ethical and methodological questions.}, author = {Stirling, Peter and Chevallier, Philippe and Illien, Gildas}, doi = {10.1045/march2012-stirling}, interhash = {a783191c99a285197525595ebf509bb2}, intrahash = {4f7840193e7e435ad5dd0003fc93691a}, issn = {1082-9873}, journal = {D-Lib Magazine}, month = {March/April }, number = {3/4}, title = {Web Archives for Researchers: Representations, Expectations and Potential Uses}, url = {http://www.dlib.org/dlib/march12/stirling/03stirling.html}, volume = 18, year = 2012 }