Re: [delicious-discuss] increasing the number of del.icio.us users reducing spam
Is it only me who believes that only someone trying to build a scoring system for Delicious would claim that it's a competitive environment? I don't personally care who's the most prolific poster, and I'm not sure it's a good idea to focus. However, let me add that I'm very interested to see the social aspects of Delicious evolve. Instead of running around trying to prevent bad people from adding unwanted items to the pool, I'd rather have tools that help me sift through the river for valuable items. I find the recommendations very useful, and would love to see more work like this. On 12/3/05, Amir Michail [EMAIL PROTECTED] wrote: Hi, Given a competitive environment for del.icio.us users (e.g., CollaborativeRank), we could allow users to further increase their scores/influence by inviting/endorsing people who they believe will contribute in a positive way. -- Brian Del Vecchio | [EMAIL PROTECTED] | http://hybernaut.com/ ___ discuss mailing list discuss@del.icio.us http://lists.del.icio.us/cgi-bin/mailman/listinfo/discuss
Re: [delicious-discuss] increasing the number of del.icio.us users reducing spam
On 12/5/05, Brian Del Vecchio [EMAIL PROTECTED] wrote: I'd rather have tools that help me sift through the river for valuable items. I find the recommendations very useful, and would love to see more work like this. I agree. I'm not interested in who is the most influential though I am VERY interested in who is the most influential when related to Chris' links. The former is a game, the latter is a tool for finding new information. One of the reasons I have stayed with del.icio.us is that I have a fair amount of trust that Joshua wants to focus on the usefulness and leverage of the social network effects to uncover and recover information. c ___ discuss mailing list discuss@del.icio.us http://lists.del.icio.us/cgi-bin/mailman/listinfo/discuss
Re: [delicious-discuss] increasing the number of del.icio.us users reducing spam
One interesting thing that I found with building the recommendation engine is that I got much more pleasing results by considering each person's tag independently rather than the person as a whole. However, from a UI standpoint, I'd like to provide people with a way to get a global view of who is recommended to them in general, presumably by aggregating the per-tag recommendations (currently too slow to be done.) Another issue I've been thinking about is the notion of influence in general; how to quantify the metric in some reasonable way? For example, if an item was posted 10 times, and person X was first, was he influential? What if the other 9 times were the same day? Or two weeks laters? What if 1000 more people were to go on to do it? I suppose something interesting might occur if you just looked at a user's urls and score every other user who bookmarked that URL before them. Alternately a bayesian predictor to suggest if person X posts something, person Y is likely to. Shame about all the I/O this would take up. Probably time to order more servers anyway. Joshua On Dec 5, 2005, at 11:25 AM, Chris Lott wrote: On 12/5/05, Brian Del Vecchio [EMAIL PROTECTED] wrote: I'd rather have tools that help me sift through the river for valuable items. I find the recommendations very useful, and would love to see more work like this. I agree. I'm not interested in who is the most influential though I am VERY interested in who is the most influential when related to Chris' links. The former is a game, the latter is a tool for finding new information. One of the reasons I have stayed with del.icio.us is that I have a fair amount of trust that Joshua wants to focus on the usefulness and leverage of the social network effects to uncover and recover information. c ___ discuss mailing list discuss@del.icio.us http://lists.del.icio.us/cgi-bin/mailman/listinfo/discuss -- joshua schachter [EMAIL PROTECTED] ___ discuss mailing list discuss@del.icio.us http://lists.del.icio.us/cgi-bin/mailman/listinfo/discuss
Re: [delicious-discuss] increasing the number of del.icio.us users reducing spam
Joshua, Another issue I've been thinking about is the notion of influence in general; how to quantify the metric in some reasonable way? For example, if an item was posted 10 times, and person X was first, was he influential? What if the other 9 times were the same day? Or two weeks laters? What if 1000 more people were to go on to do it? I do wonder about a strict first-in principle as a reliable predictor of influence. Golder and Huberman's research showed that there was quite a bit of variation in volume of tag use to given urls over time. Some urls had an expected immediate spike in use after first post, followed by a smooth, rapid decay. Others, however, had several bursts of activity as the url was rediscovered months after the first post. I believe they even found urls that had their biggest peaks in use late in their del.icio.us history. So in the latter cases, would you factor in the users on the front-end of the later spikes in activity as well? Shame about all the I/O this would take up. Probably time to order more servers anyway. With all the computation, might want to bring in some more power and a/c as well... ;-) BTW, this is great stuff! I am really impressed that you guys are sharing these issues in public rather than putting everything in the ip black box (not that I think you shouldn't be able to profit from the hard work!). Allowing Golder and Huberman to use your data was fantastic. It not only legitimizes del.icio.us, but helps to highlight a lot of the key discussions in the information retrieval community. best, geoff froh seattle, usa ___ discuss mailing list discuss@del.icio.us http://lists.del.icio.us/cgi-bin/mailman/listinfo/discuss
[delicious-discuss] increasing the number of del.icio.us users reducing spam
Hi, I think that perhaps there's a way to increase the number of del.icio.us users and reduce spam at the same time. The idea is to use an invitation or endorsement system with consequences. Given a competitive environment for del.icio.us users (e.g., CollaborativeRank), we could allow users to further increase their scores/influence by inviting/endorsing people who they believe will contribute in a positive way. If those invited/endorsed people do in fact contribute in a positive way (as measured by the competitive environment), then those who invited them are rewarded with greater score/influence. If those invited/endorsed people contribute in a negative way, then those who invited them are penalized. At this point, the inviters can cut their losses by flagging these people as unhelpful. Note that I am not necessarily suggesting an invitation only scheme. You could endorse existing del.icio.us users for example if you believe they will raise your score/influence. It would be interesting to see how people might try to game this system. Would creating multiple accounts help for example? Amir ___ discuss mailing list discuss@del.icio.us http://lists.del.icio.us/cgi-bin/mailman/listinfo/discuss