%0 Conference Paper %1 gossen2017extracting %A Gossen, Gerhard %A Demidova, Elena %A Risse, Thomas %B Proceedings of the 21st International Conference on Theory and Practice of Digital Libraries %D 2017 %I Springer %K alexandria data4urbanmobility gossen icrawl myown %P 116-127 %R https://doi.org/10.1007/978-3-319-67008-9_10 %T Extracting Event-Centric Document Collections from Large-Scale Web Archives %U https://link.springer.com/chapter/10.1007%2F978-3-319-67008-9_10 %V 10450 %X Web archives are typically very broad in scope and extremely large in scale. This makes data analysis appear daunting, especially for non-computer scientists. These collections constitute an increasingly important source for researchers in the social sciences, the historical sciences and journalists interested in studying past events. However, there are currently no access methods that help users to efficiently access information, in particular about specific events, beyond the retrieval of individual disconnected documents. Therefore we propose a novel method to extract event-centric document collections from large scale Web archives. This method relies on a specialized focused extraction algorithm. Our experiments on the German Web archive (covering a time period of 19 years) demonstrate that our method enables the extraction of event-centric collections for different event types. %@ 978-3-319-67008-9

@inproceedings{gossen2017extracting, abstract = {Web archives are typically very broad in scope and extremely large in scale. This makes data analysis appear daunting, especially for non-computer scientists. These collections constitute an increasingly important source for researchers in the social sciences, the historical sciences and journalists interested in studying past events. However, there are currently no access methods that help users to efficiently access information, in particular about specific events, beyond the retrieval of individual disconnected documents. Therefore we propose a novel method to extract event-centric document collections from large scale Web archives. This method relies on a specialized focused extraction algorithm. Our experiments on the German Web archive (covering a time period of 19 years) demonstrate that our method enables the extraction of event-centric collections for different event types.}, added-at = {2017-07-13T13:54:22.000+0200}, author = {Gossen, Gerhard and Demidova, Elena and Risse, Thomas}, biburl = {https://www.bibsonomy.org/bibtex/2174c46d0b84c804c62506e4d517365c1/demidova}, booktitle = {Proceedings of the 21st International Conference on Theory and Practice of Digital Libraries}, doi = {https://doi.org/10.1007/978-3-319-67008-9_10}, interhash = {67803c4f3e1bea57dbc519db815bd2e7}, intrahash = {174c46d0b84c804c62506e4d517365c1}, isbn = {978-3-319-67008-9}, keywords = {alexandria data4urbanmobility gossen icrawl myown}, language = {English}, pages = {116-127}, publisher = {Springer}, series = {Lecture Notes in Computer Science}, timestamp = {2017-12-22T12:00:40.000+0100}, title = {Extracting Event-Centric Document Collections from Large-Scale Web Archives}, url = {https://link.springer.com/chapter/10.1007%2F978-3-319-67008-9_10}, volume = 10450, year = 2017 }