Classifier Calibration for Multi-Domain Sentiment Classification.
conference paper
Textual sentiment classifiers classify texts into a fixed number of affective classes, such as positive, negative or neutral sentiment, or subjective versus objective information. It has been observed that sentiment classifiers suffer from a lack of generalization capability: a classifier trained on a certain domain generally performs worse on data from another domain.
This phenomenon has been attributed to domain-specific affective vocabulary. In this paper1, we propose a voting-based thresholding approach, which calibrates a number of existing single-domain classifiers with respect to sentiment data from a new domain. The approach presupposes only a small amount of annotated data from the new domain. We evaluate three criteria for estimating thresholds, and discuss the ramifications of these criteria for the trade-off between classifier performance and manual annotation effort.
Textual sentiment classifiers classify texts into a fixed number of affective classes, such as positive, negative or neutral sentiment, or subjective versus objective information. It has been observed that sentiment classifiers suffer from a lack of generalization capability: a classifier trained on a certain domain generally performs worse on data from another domain. This phenomenon has been attributed to domain-specific affective vocabulary. In this paper, we propose a voting-based thresholding approach, which calibrates a number of existing single-domain classifiers with respect to sentiment data from a new domain. The approach presupposes only a small amount of annotated data from the new domain. We evaluate three criteria for estimating thresholds, and discuss the ramifications of these criteria for the trade-off between classifier performance and manual annotation effort.
This phenomenon has been attributed to domain-specific affective vocabulary. In this paper1, we propose a voting-based thresholding approach, which calibrates a number of existing single-domain classifiers with respect to sentiment data from a new domain. The approach presupposes only a small amount of annotated data from the new domain. We evaluate three criteria for estimating thresholds, and discuss the ramifications of these criteria for the trade-off between classifier performance and manual annotation effort.
Textual sentiment classifiers classify texts into a fixed number of affective classes, such as positive, negative or neutral sentiment, or subjective versus objective information. It has been observed that sentiment classifiers suffer from a lack of generalization capability: a classifier trained on a certain domain generally performs worse on data from another domain. This phenomenon has been attributed to domain-specific affective vocabulary. In this paper, we propose a voting-based thresholding approach, which calibrates a number of existing single-domain classifiers with respect to sentiment data from a new domain. The approach presupposes only a small amount of annotated data from the new domain. We evaluate three criteria for estimating thresholds, and discuss the ramifications of these criteria for the trade-off between classifier performance and manual annotation effort.
Topics
TNO Identifier
445974
Publisher
The AAAI Press
Source title
Proceedings of the Fourth International Conference on Weblogs and Social Media, ICWSM 2010, Washington, DC, USA, May 23-26
Editor(s)
Cohen, W.W.
Gosling, S.
Gosling, S.
Place of publication
Palo Alto, CA, USA
Pages
311-314