Talk:Extended Epinions dataset

From TrustLet, a free, collaborative project for collecting and analyzing information about trust metrics.

Revision as of 11:51, 19 July 2008 by PaoloMassa (Talk | contribs)
(diff) ←Older revision | Current revision (diff) | Newer revision→ (diff)
Jump to: navigation, search

What is the exact time of the dataset? --Ustcchensu 04:37, 4 March 2008 (PST)

Hi Ustcchensu. You want to know when I received it? I'm not sure about it but I believe in early 2005 or in late 2004. --PaoloMassa 04:43, 18 March 2008 (PDT)
Thanks!You're so kind:)--210.76.196.71 22:41, 8 April 2008 (PDT)
thanks ;-) --PaoloMassa 08:41, 10 April 2008 (PDT)
Hi!Paolo. Could you tell the meaning of VERTICAL_ID in the extended epinion's dataset?Thank you!--Ustcchensu 07:07, 13 July 2008 (PDT)
Hi! I'm sorry but I was not told the meaning of vertical_id ;( --PaoloMassa 08:17, 13 July 2008 (PDT)
I've notice some variances in the extended dataset. For example, 38 reviews in rating.txt have no author information in mc.txt. I've also notice that the amount of users in user_rating.txt is 131827, the amount of users calculated from rating.txt and mc.txt is 195804. I guess these users and are just a small part of the total users in Epinion when the dataset was sent to you. Do you know how the dataset was sampled from the whole data in Epinion(i.e. the rules)? I believe it is crucial for evaluting trust metric algorithms with the data. Thank you!--Ustcchensu 07:23, 18 July 2008 (PDT)
I'm sorry I don't have this information ;( --PaoloMassa 04:51, 19 July 2008 (PDT)
Personal tools