Since no large amount of labeled training data for our new notion of sentiment relevance is available, we investigate two semi-supervised methods for creating sentiment relevance classifiers: a distant supervision approach that leverages structured information about the domain of the reviews; and transfer learning on feature representations based on lexical taxonomies that enables knowledge transfer.

In this section, we show how to bootstrap a sentiment relevance classifier by distant supervision (DS) .

Even though we do not have sentiment relevance annotations, there are sources of metadata about the movie domain that we can leverage for distant supervision .

We call these labels inferred from NE metadata distant supervision (DS) labels.

Distant supervision and transfer learning are settings where exact training data is unavailable.

The first approach is distant supervision (DS).

results of our experiments on distant supervision (Section 6) and transfer learning (Section 7).

Their setup differs from ours as our focus lies on pattern-based distant supervision instead of distant supervision using documents for sentence classification.