Mining fine-grained opinions on closed captions of YouTube videos with an attention-RNN
This addresses the problem of analyzing opinions in video reviews for researchers and practitioners, but it is incremental as it adapts existing methods to a new data type.
The authors tackled fine-grained opinion mining on YouTube video closed captions by introducing a new dataset and an attention-RNN model, achieving state-of-the-art performance on aspect extraction without hand-crafted features on SemEval and outperforming baselines on their dataset, though with performance drops compared to written text.
Video reviews are the natural evolution of written product reviews. In this paper we target this phenomenon and introduce the first dataset created from closed captions of YouTube product review videos as well as a new attention-RNN model for aspect extraction and joint aspect extraction and sentiment classification. Our model provides state-of-the-art performance on aspect extraction without requiring the usage of hand-crafted features on the SemEval ABSA corpus, while it outperforms the baseline on the joint task. In our dataset, the attention-RNN model outperforms the baseline for both tasks, but we observe important performance drops for all models in comparison to SemEval. These results, as well as further experiments on domain adaptation for aspect extraction, suggest that differences between speech and written text, which have been discussed extensively in the literature, also extend to the domain of product reviews, where they are relevant for fine-grained opinion mining.