Dataset Groups Activity Stream ClueWeb09B The ClueWeb09B collection is a large-scale web search dataset, containing 31 million web pages, 31 million queries, and 1.5 billion documents. BibTex: @dataset{Claudio_Lucchese_and_Salvatore_Orlando_and_Raffaele_Perego_and_Fabrizio_Silvestri_and_Gabriele_Tolomei_2025, abstract = {The ClueWeb09B collection is a large-scale web search dataset, containing 31 million web pages, 31 million queries, and 1.5 billion documents.}, author = {Claudio Lucchese and Salvatore Orlando and Raffaele Perego and Fabrizio Silvestri and Gabriele Tolomei}, doi = {10.57702/umzg8xjn}, institution = {No Organization}, keyword = {'ClueWeb', 'ClueWeb09B', 'Information Retrieval', 'Web Search Evaluation', 'information retrieval', 'web search'}, month = {jan}, publisher = {TIB}, title = {ClueWeb09B}, url = {https://service.tib.eu/ldmservice/dataset/clueweb09b}, year = {2025} }
