Author's Sentiment Prediction
This work addresses the challenge of entity sentiment analysis in news articles, but it is incremental as it primarily introduces a new dataset without proposing a novel solution.
The authors tackled the problem of predicting author sentiment towards entities in news articles by introducing PerSenT, a dataset with 5.3k documents and 38k paragraphs covering 3.2k unique entities, and found that existing methods like BERT fine-tuning and paragraph-level aggregation were ineffective for this difficult classification task.
We introduce PerSenT, a dataset of crowd-sourced annotations of the sentiment expressed by the authors towards the main entities in news articles. The dataset also includes paragraph-level sentiment annotations to provide more fine-grained supervision for the task. Our benchmarks of multiple strong baselines show that this is a difficult classification task. The results also suggest that simply fine-tuning document-level representations from BERT isn't adequate for this task. Making paragraph-level decisions and aggregating them over the entire document is also ineffective. We present empirical and qualitative analyses that illustrate the specific challenges posed by this dataset. We release this dataset with 5.3k documents and 38k paragraphs covering 3.2k unique entities as a challenge in entity sentiment analysis.