ACM SIGCHI General Interest Announcements (Mailing List)


Options: Use Forum View

Use Monospaced Font
Show Text Part by Default
Show All Mail Headers

Message: [<< First] [< Prev] [Next >] [Last >>]
Topic: [<< First] [< Prev] [Next >] [Last >>]
Author: [<< First] [< Prev] [Next >] [Last >>]

Print Reply
Jaap Kamps <[log in to unmask]>
Reply To:
Jaap Kamps <[log in to unmask]>
Wed, 7 May 2014 11:28:36 +0200
text/plain (72 lines)
Third Contextual Suggestion Track

Text REtrieval Conference (TREC 2014)

November 18-21, Gaithersburg MD, USA

Submissions Due: July 21, 2014

* Call for Participants

The Contextual Suggestion track considers a complex information need, 
highly dependent on context, which nonetheless can be simply expressed. 
  The track focuses on one situation: a user with a mobile device with 
limited interaction but some sort of user profile; who is in a strange 
town; and who is looking for something to do.  There is no explicit 
query: the implicit query is “here I am, what should I do?”.

Given a profile (likes and dislikes of attractions) and a context (new 
city) pair, participants should return a ranked list of up to 50 ranked 
suggestions.  Each suggestion should be appropriate to the profile 
(based on the user’s preferences) and the context (according to the 
location).  Profiles correspond to the stated preferences of real 
individuals, who will return to judge proposed suggestions.

Participating groups will be given:
- A set of profiles for each user (like and dislikes for 100 attractions 
in two cities).
- A set of geographical contexts (50 randomly selected US cities) that 
the system should target.

In order to find candidate suggestions, a system may use:
- URLs from the open Web
- ClueWeb12 <>
- ClueWeb12 B13 (7% of all of ClueWeb12)

Additionally, participants may use other available resources, such as 
Google Places, etc.  Training data is available in the form of judged 
profile+context pairs from the TREC 2012 and 2013 version of this track.

* We Need Your Help!

Help us define the best methods of suggesting attractions:

- Sign up now!
- Start investigating the problem with the contexts (available already) 
and profiles (available on June 2).
- Submit suggestions by July 21.
- Participate in the track workshop in November.

* Further details

See the Contextual Suggestion Track guidelines at

Sign up for TREC'14 at

Mailing list: Send a mail message to listproc (at) such that 
the body consists of the line subscribe trec-context <FirstName> <LastName>

    For news of CHI books, courses & software, join CHI-RESOURCES
     mailto: [log in to unmask]

    To unsubscribe from CHI-ANNOUNCEMENTS send an email to
     mailto:[log in to unmask]

    For further details of CHI lists see