Beyond Sentiment: The Manifold of Human Emotions

By Seungyeon Kim, Fuxin Li, Guy Lebanon, Irfan Essa. 2012

36 citations recorded by the source corpus.

Sentiment analysis predicts the presence of positive or negative emotions in a text document. In this paper we consider higher dimensional extensions of the sentiment concept, which represent a richer set of human emotions. Our approach goes beyond previous work in that our model contains a continuous manifold rather than a nite set of human emotions. We investigate the resulting model, compare it to psychological observations, and explore its predictive capabilities. Besides obtaining signicant improvements over a baseline without manifold, we are also able to visualize dierent notions of positive sentiment in dierent domains.

Subfields: Artificial Intelligence, Natural Language Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Parikshit Ram
2. Alexander G. Gray
3. Ryan R. Curtin
4. Ann B. Lee
5. Rafael Izbicki

In Natural Language Processing

1. Alexander G. Gray
2. Parikshit Ram

Citations in the corpus

• Maximum inner-product search using cone trees (2012, methodology): “For text data, we use the LiveJournal blog moods data set [19].”
• Fast Exact Max-Kernel Search (2012, methodology): “We use two different classes of datasets – (1) Datasets with fixed-length objects: These include the MNIST dataset [28], the Isomap “Images” dataset, several datasets from the UCI machine learning repository [29], three collaborative filtering datasets (MovieLens, Netflix [30], Yahoo! Music [7]), th”