Distant supervision for emotion detection using Facebook reactions
This work addresses emotion detection for social media analysis, but it is incremental as it applies an existing method to new data with modest gains.
The authors tackled emotion detection by using Facebook reactions as distant supervision to train an SVM classifier, achieving competitive results on existing benchmarks without relying on handcrafted lexicons.
We exploit the Facebook reaction feature in a distant supervised fashion to train a support vector machine classifier for emotion detection, using several feature combinations and combining different Facebook pages. We test our models on existing benchmarks for emotion detection and show that employing only information that is derived completely automatically, thus without relying on any handcrafted lexicon as it's usually done, we can achieve competitive results. The results also show that there is large room for improvement, especially by gearing the collection of Facebook pages, with a view to the target domain.