Judges’ Queries and Presenter’s Replies

  • May 20, 2013 | 07:26 p.m.

    how accurately are you able to identify transportation events and localize them?

  • Icon for: Roland Varriale

    Roland Varriale

    Presenter
    May 21, 2013 | 10:44 p.m.

    Hello Dr. Hirschberg thank you for your interest. We are currently able to identify transportation events with 94% accuracy. Unfortunately the localization of the tweets is relatively low based on sole use of twitter location data or user input data. We are currently addressing this by cross referencing locations and landmarks mentioned in tweets by using a geo-dictionary, or gazetteer. By using this inferred data we hope to achieve a higher — and more precise — amount of location data.

  • May 21, 2013 | 10:13 p.m.

    VTIS notifies users if any transportation event will have an effect on their experience during their travel route. Will you allow users to provide feedback (in real time or at a later time) about the notifications they received, and is it possible to utilize this feedback in improving the effectiveness of VTIS and perhaps modifying the notifications to subsequent users who are affected by the same event?

  • Icon for: Roland Varriale

    Roland Varriale

    Presenter
    May 21, 2013 | 10:47 p.m.

    That is a future consideration for this project once the initial system is fully deployed. There are trust, reputation, and uncertainty components that will need to be addressed at that time. Once all of these facets have been integrated the VTIS will also accomodate input from users as well as feedback on that form of input as well.

  • May 21, 2013 | 10:21 p.m.

    What other sources of transportation event data could possibly be combined with Twitter data to improve your identification and localization?

  • Icon for: Roland Varriale

    Roland Varriale

    Presenter
    May 21, 2013 | 10:51 p.m.

    In papers such as “Traffic Observatory: a system to detect and locate traffic events and conditions using Twitter” by Ribeiro et al. my previously mentioned method is discussed. By combining prior knowledge of geolocational data we can provide a more accurate placement of an event. For example, if a landmark such as the Empire State Building was mentioned within a tweet with a transportation event there is no explicit location; however, by accessing a geolocational reference such as a gazetteer we could provide a localization to the tweet that could not be extracted simply from the plaintext.

  • Further posting is closed as the competition has ended.

Presentation Discussion

  • Icon for: Edinah Gnang

    Edinah Gnang

    Trainee
    May 23, 2013 | 05:42 p.m.

    Great job ! Does your model also account for the traffic reaction to the received messages ?

  • Icon for: Roland Varriale

    Roland Varriale

    Presenter
    May 23, 2013 | 05:56 p.m.

    That is a very interesting consideration. We don’t currently model that; however, if the affect of our system grows that may be necessary functionality that would need to be included.

  • May 23, 2013 | 06:09 p.m.

    This looks very interesting – I noticed the following on the post – “The user must also specify some amount of tolerance to transportation events they wish to endure.” I’m wondering what kind of scale you’re using and what this looks like to the user?

  • Icon for: Roland Varriale

    Roland Varriale

    Presenter
    May 23, 2013 | 06:12 p.m.

    Thank you for your interest. The user would input some amount of tolerance on a scale of 1-10 where 10 is the highest tolerance. The user would specify this when they created the route via a simple drop down box.

    Because of user preference we feel this is an important aspect that should be determined on a user by user basis.

  • Further posting is closed as the competition has ended.

Icon for: Roland Varriale

ROLAND VARRIALE

University of Illinois at Chicago
Years in Grad School: 1

VTIS: A Volunteered Information System

We have devised a system that will generate personalized notifications for users based on a provided path, temporal range, and set of transportation modes. At a high level, the functionality of this system is to identify events that affect the user’s route and notify the user of these events. The VTIS will provide a robust multimodal notification system based on information from several sources. This information will be combined to create a repository of transportation events, which may be queried to notify affected users. Users will create routes through the VTIS by specifying a series of directions. The user will then be notified if any transportation event will have an effect on the user’s experience during that route.