Best Paper Award for the 9th International Conference on Social Computing and Social Media, in the context of HCI International 2017, 9 - 14 July 2017, Vancouver, Canada

Certificate for Best Paper Award of the 9th International Conference on Social Computing and Social Media
conferred to

Sebastian Perez-Vera, Rodrigo Alfaro and Hector Allende-Cid
(Pontificia Universidad Católica de Valparaíso, Chile)

for the paper entitled

"Intent Classification of Social Media Texts with Machine Learning for Customer Service Improvement"

Presented in the context of
HCI International 2017
9 - 14 July 2017, Vancouver, Canada

Paper Abstract
"Social media platforms in the last few years have facilitated the development of communities that discuss real-world events, and have shaped the way users interact. The content generated in these platforms reflect a variety of intentions, ranging from social interaction to commercial interest, among many others. The present study aims at the implementation of an automatic intent classification system for a Chilean electricity company social media account.

The dataset was created from 5000 tweets that were manually classified by 5 people. If discrepancies were detected, a majority voting scheme was used in order to tag the tweets’ intentions. In order to perform the experimental validation of the automatic classification with the machine learning algorithms, several text representations were used (tf-idf, tf-rfl and bin-rfl). The results obtained from the various tests that were conducted yielded satisfactory results. We also analyzed how to assign automatic responses to frequently asked questions, and obtained promising results."

The full paper is available through SpringerLink, provided that you have proper access rights.