Introducing WIkimatix.com: A mashup for wikifying Google Trend's top search keywords. Moreover you can "disqus" and comment on recent hot topics being searched for right now!
Yesterday, while taking a break from writing my dissertation I was looking at the top search terms over at Google Trends. Few things immediately came to my mind:
- I am a Wikipedia and News junkie -- no surprise there! Sometimes, I do not know a whole lot about the top search trerms and have to look up the wikipedia entry to refresh my mind about the topic or person. BTW, have you noticed that so many of the top terms are named entities? I also spoke about this in my earlier post on Intrestingness and Feshness in Search.
- Google trends does not have an ability to discuss. I wanted something where I could comment on the terms in a digg like fashion? Perhaps talk to everyone about what I think of this whole "Big foot thing in the news". (Tip of the hat to the awesome widgets powered by Disqus)
- Finally, I would like to know exactly why something is in the News or has made it to a top 100 list. I just want a one or two line snippet/summary and a pointer to the most authoritative blog post/news piece about this keyword. While Wikimatix currently does not provide this -- it is something that can be easily extended.
Well, this was a quick hack ( ~150-200 lines of code; ~2 hours) and is meant to be a prototype/proof of concept idea. I think there can be a lot one can do with the idea of capturing the buzz using query logs and having discussions around the search terms and the latest news.
Note: Wikimatix updates itself every two hours. The disqus pages are associated with the individual search term and thus can be accessed even after the term is no longer buzzy.
Some possible improvements that might be good:
- Group related search terms like "big foot", "big foot discovery" etc
- Name disambiguation can be a problem. Sometimes the right person's Wikipedia entry is hard to determine without the context of the story.
- Simple heuristics might work rather well to identify the top categories that are in the news. For instance, today it is all about "Big foot", "Olympics" and a few other major events.
- For search terms, there might be a good video, photograph associated with it. It would be cool to display that as well.
I just looked at this tool, and went aha!
Make sure you share this around, this has great potential. If possible, you should go beyond Google's hotlist. I know Yahoo!, Live and Ask also have these.
Posted by: Pranam Kolari | August 16, 2008 at 04:41 AM
Looking further at the abstracts, it seemed much effort should go to improve it. I would suggest improving abstracts/summaries as the most important next update, in your next dissertation writing break :)
So I guess with Wikimatix:
(a) You attract users through smart abstracts (text, audio, video)
(b) You engage and retain them through commenting system
Collective intelligence, and all the goodies follow.
Aha!
Posted by: Pranam Kolari | August 16, 2008 at 04:54 AM
Thanks Pranam, you are right on the money! Thats exactly the idea behind wikimatix. As I get some more time, I will try to improve the abstracts and add search/archive/most commented stories features.
Posted by: Akshay Java | August 16, 2008 at 02:46 PM
Ashkay --
this is cool but it needs more "why" content. For instance, today's Cloris Leachman top entry doesn't mention why she's in the news or a hot search. You might pull Google News hits, which tend to explain better why someone is on the public mind.
Cool stuff though! Let us know when it's improved & we can do something for UMBC Web site & maybe mass media interest.
Posted by: Charles | August 18, 2008 at 09:34 AM
Akshay,
Great hack! We've been batting around some similar ideas at Juice. Sal made a python library for accessing google trends data: Google Trends API
The named entity aspects are very interesting, I could see clustering the trends as a possible direction (hot people, places, events etc.)
-Pete
Posted by: Peter Skomoroch | August 18, 2008 at 10:21 AM
Hi Charles,
Thanks for the note! I agree that improving abstracts with snippets from Google and images/videos that would better explain the "why" would be great. I am gonna try and find more time to work on this further during my breaks while I finish my writeup! I will keep you posted and as soon as I have a more polished version ready I should be able to share it on UMBC/Media relations.
Thanks
Akshay
Posted by: Akshay Java | August 18, 2008 at 10:38 AM
Dang! This is just awesome Pete! You made my life so much easier. I wish I had found your API sooner. I would love to use it to work on the next version of Wikimatix. BTW, do you guys have a demo or some sneak peek I could get access to over at Juice?
Thanks
Akshay
Posted by: Akshay Java | August 18, 2008 at 10:55 AM
Yes indeed with with this new tech with this info about "improving abstracts with snippets from Google and images/videos"
Posted by: Busby SEO Test | December 01, 2008 at 07:30 AM
Thanks.
For sharing the great article .
Disqus rocks ! ! !
Posted by: davis | December 03, 2008 at 03:14 PM
It's very nice information, it will to using it
Posted by: Fuziosurveys | December 13, 2008 at 08:46 PM
I think Disqus is going to be the next best thing in commenting. It's great at stopping spam!....... : )
Posted by: Jhonez | March 31, 2009 at 03:19 PM
Looking further at the abstracts, it seemed much effort should go to improve it. I would suggest improving abstracts/summaries as the most important next update, in your next dissertation writing break :)
Posted by: Speedocar | June 15, 2009 at 04:12 PM