%0 Conference Paper %1 Vo:2016:WFD:2908131.2908165 %A Vo, Khoi Duy %A Tran, Tuan %A Nguyen, Tu Ngoc %A Zhu, Xiaofei %A Nejdl, Wolfgang %B Proceedings of the 8th ACM Conference on Web Science %C New York, NY, USA %D 2016 %I ACM %K alexandria %P 173--182 %R 10.1145/2908131.2908165 %T Can We Find Documents in Web Archives Without Knowing Their Contents? %U https://arxiv.org/abs/1701.03942 %X Recent advances of preservation technologies have led to an increasing number of Web archive systems and collections. These collections are valuable to explore the past of the Web, but their value can only be uncovered with effective access and exploration mechanisms. Ideal search and ranking methods must be robust to the high redundancy and the temporal noise of contents, as well as scalable to the huge amount of data archived. Despite several attempts in Web archive search, facilitating access to Web archive still remains a challenging problem. In this work, we conduct a first analysis on different ranking strategies that exploit evidences from metadata instead of the full content of documents. We perform a first study to compare the usefulness of non-content evidences to Web archive search, where the evidences are mined from the metadata of file headers, links and URL strings only. Based on these findings, we propose a simple yet surprisingly effective learning model that combines multiple evidences to distinguish "good" from "bad" search results. We conduct empirical experiments quantitatively as well as qualitatively to confirm the validity of our proposed method, as a first step towards better ranking in Web archives taking metadata into account. %@ 978-1-4503-4208-7

@inproceedings{Vo:2016:WFD:2908131.2908165, abstract = {Recent advances of preservation technologies have led to an increasing number of Web archive systems and collections. These collections are valuable to explore the past of the Web, but their value can only be uncovered with effective access and exploration mechanisms. Ideal search and ranking methods must be robust to the high redundancy and the temporal noise of contents, as well as scalable to the huge amount of data archived. Despite several attempts in Web archive search, facilitating access to Web archive still remains a challenging problem. In this work, we conduct a first analysis on different ranking strategies that exploit evidences from metadata instead of the full content of documents. We perform a first study to compare the usefulness of non-content evidences to Web archive search, where the evidences are mined from the metadata of file headers, links and URL strings only. Based on these findings, we propose a simple yet surprisingly effective learning model that combines multiple evidences to distinguish "good" from "bad" search results. We conduct empirical experiments quantitatively as well as qualitatively to confirm the validity of our proposed method, as a first step towards better ranking in Web archives taking metadata into account.}, acmid = {2908165}, added-at = {2016-09-22T14:37:41.000+0200}, address = {New York, NY, USA}, author = {Vo, Khoi Duy and Tran, Tuan and Nguyen, Tu Ngoc and Zhu, Xiaofei and Nejdl, Wolfgang}, biburl = {https://www.bibsonomy.org/bibtex/211fefe50c2caf9c15bb1376835887539/alexandriaproj}, booktitle = {Proceedings of the 8th ACM Conference on Web Science}, doi = {10.1145/2908131.2908165}, interhash = {cc4ec0cdb49ae6223d3f76215b0b565f}, intrahash = {11fefe50c2caf9c15bb1376835887539}, isbn = {978-1-4503-4208-7}, keywords = {alexandria}, location = {Hannover, Germany}, numpages = {10}, pages = {173--182}, publisher = {ACM}, series = {WebSci '16}, timestamp = {2017-04-10T11:56:19.000+0200}, title = {Can We Find Documents in Web Archives Without Knowing Their Contents?}, url = {https://arxiv.org/abs/1701.03942}, year = 2016 }