🎉🎉 "Trend Analysis of Lebanese Road Crashes in 2022" has been released [Report].
LOCR platform serves to collect and analyze road crash events using crowd-sourcing approach from social media (notably Twitter and Facebook). Developed by a group led by Dr Ali J. Ghandour, LOCR has been in production since 2015 at the National Center for Remote Sensing – CNRS.
LOCR is the only real-time and openly available Lebanese spatio-temporal road crashes database. Events collection, classification and visualization is done autonomously, without any human intervention, by employing Natural Language Processing (NLP) techniques. Fine-grained data and comprehensive reporting is not the objective of this work, but rather LOCR serves to mine and analyze spatio-temporal road crashes trends using representative time-series. The data collected from this work has proven itself to be credible and has been used in multiple research projects so far [LINK]. Note that the parsed tweets and posts are not geotagged and hence the fetched crashes locations are not exact GPS coordinate.
[SLIDES] that summarizes major milestones and achievements as part of the LOCR project.
Researchers interested to access the LOCR dataset can reach out via contact widget Contact or through email aghandour at cnrs.edu.lb.
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.