#SarcasmDetection is soooo general! Towards a Domain-Independent Approach for Detecting Sarcasm
This addresses the challenge for researchers and practitioners needing to transfer sarcasm detection methods across domains, but it is incremental as it builds on existing feature-based approaches.
The paper tackled the problem of domain dependence in sarcasm detection by developing a general feature set and evaluating training scenarios, achieving an F1 of 0.780 with domain adaptation, which outperforms baselines of 0.515 and 0.345 and prior work.
Automatic sarcasm detection methods have traditionally been designed for maximum performance on a specific domain. This poses challenges for those wishing to transfer those approaches to other existing or novel domains, which may be typified by very different language characteristics. We develop a general set of features and evaluate it under different training scenarios utilizing in-domain and/or out-of-domain training data. The best-performing scenario, training on both while employing a domain adaptation step, achieves an F1 of 0.780, which is well above baseline F1-measures of 0.515 and 0.345. We also show that the approach outperforms the best results from prior work on the same target domain.