Multi-modal Chinese Text Emotion Metaphor Computation Based on Mutual Information and Information Entropy

Metaphor is to express another thing through one thing, it not only a rhetorical means, but also embodies kind of analogical cognition and way thinking people. In recent years, metaphors have made more progress in Chinese language recognition, so their status has gradually risen. sentiment analysis relatively difficult problem processing. semantics ambiguous complex, great challenge construct Emotion structure. this paper, nouns verbs are used as test samples conduct metaphor calculation. The results mutual information entropy show that for the sample calculation, correct rate individual words less than 70%. ratio between macro-average gerund baseline fluctuates large. recognition about 20% higher original 10% verbs. It shows under action entropy, performance basic structure constructed from perspective improved, further illustrates feasibility algorithm building