knowledge_graph_attention_network
knowledge_graph_attention_network copied to clipboard
xiangwang1223
Questions about dataset LastFM
According the link you provided in the paper, I found the LastFM dataset. But the statistic of datasets are different between the original dataset and the dataset you provided here. For example, the number of users and items are 23565 and 48122, respectively. However, the statistics are 1892 users and 17632 artists in the original dataset. Why? And I also want to ask you that is the item id here is same as the artist id in the original dataset. Is it possible for me to understand that you just sorted the history of individual users into one line? Thank you for your answsering.
Hi, Thanks for your interests. Sorry for the late reply after a busy week.
-
Please visit the LFM-1b to obtain the original version of Last-FM dataset, which has around 120,000 users. For more details, please refer to the LFM-1b paper.
-
In the original dataset, the listening list includes the artist, album, and track, as well as a timestamp. As such, we can get a sorted personal history.
Thanks.
HI, for the answer 2, does it mean that the item list of one user is sorted by the time? In another word, the latter one is listened by the user later than the former one? And the test set is later than the train set, right? Are other datasets processed in the same way? Looking sincerely for ur reply!
Sorry for the late reply after a busy week. Yes, all datasets are processed chronologically.
Hi Xiang, Thanks for referring to LastFM data and the paper. Based on LastFM paper, the data ranges from January 2013 to August 2014. Your paper mentions that a subset of data from Jan 2015 to June 2015 was used. Could you please advise on this?
