We introduce a novel framework based on the probabilistic model for emotion wording assistance. The example sentences from the online dictionary, Vocabulary.com are utilized as the training data; and the writings in a designed ESL's writing task are the testing corpus. The emotion events are captured by extracting patterns of the example sentences. Our approach learns the joint probability of contextual emotion events and the emotion words from the training corpus. After extracting patterns in the testing corpus, we then aggregate their probabilities to suggest the emotion word that describes the ESL's context most appropriately. We evaluate the proposed approach by the NDCG@5 of the suggested words for the writings in the testing corpus. The experiment result shows our approach can more appropriately suggest the emotion words compared to SVM, PMI and two representative on-line reference tools, PIGAI and Thesaurus.com.
展开▼
