IJCNLP-2017 Task 4: Customer Feedback Analysis.

TLDR

The IJCNLP 2017 Shared Task on Customer Feedback Analysis was introduced to benchmark sentiment analysis across four languages. The task provided annotated corpora in English, French, Spanish, and Japanese, using a shared meanings categorization refined from an ADAPT‑Microsoft pivot study. Twenty teams participated, twelve submitted results, and the shared task demonstrated reasonably good performance across the four languages, with nine system description papers archived.

Abstract

This document introduces the IJCNLP 2017 Shared Task on Customer Feedback Analysis. In this shared task we have prepared corpora of customer feedback in four languages, i.e. English, French, Spanish and Japanese. They were annotated in a common meanings categorization, which was improved from an ADAPT-Microsoft pivot study on customer feedback. Twenty teams participated in the shared task and twelve of them have submitted prediction results. The results show that performance of prediction meanings of customer feedback is reasonable well in four languages. Nine system description papers are archived in the shared tasks proceeding.