Distant Supervision for Tweet Classification Using YouTube Labels
Walid Magdy, Hassan Sajjad, Tarek El-Ganainy, Fabrizio Sebastiani · Proceedings of the International AAAI Conference on Web and Social Media · 2021
We study an approach to tweet classification based on distant supervision, whereby we automatically transfer labels from one social medium to another. In particular, we apply classes assigned to YouTube videos to tweets linking to these videos. This provides for free a virtually unlimited number of labelled instances that can be used as training data. The experiments we have run show that a tweet classifier trained via these automatically labelled data substantially outperforms an analogous classifier trained with a limited amount of manually labelled data.