TensSent: a tensor based sentimental word embedding method
| Autor: | Mohammad Mehdi Homayounpour, Zahra Rahimi |
|---|---|
| Rok vydání: | 2021 |
| Předmět: |
Word embedding
business.industry Polarity (physics) Computer science Sentiment analysis 02 engineering and technology computer.software_genre Artificial Intelligence Tensor (intrinsic definition) 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing Artificial intelligence business Representation (mathematics) computer Feature learning Natural language processing Word (computer architecture) |
| Zdroj: | Applied Intelligence. 51:6056-6071 |
| ISSN: | 1573-7497 0924-669X |
| DOI: | 10.1007/s10489-020-02163-8 |
| Popis: | The representation of words as vectors, conventionally known as word embeddings, has drawn considerable attention in recent years as feature learning techniques for natural language processing. The majority of these methods operate solely on the semantic and the syntactic aspects of a text, remaining oblivious to sentimental information. However, as numerous words with opposite polarities may appear in similar contexts, such as “interesting” and “boring”, the exclusive use of context-oriented information lacks the required particulars for generating word embeddings as features in sentiment analysis. Along this thread, the present study proposes two novel unsupervised models to integrating word polarity information and word co-occurrences as more tailored features for sentiment analysis. Word polarity and co-occurrence come together in the form of a tensor and tensor factorization is employed for generating the word embeddings. The experimental results on IMDB and SemEval-task2 datasets demonstrate the relatively higher performance of the proposed method compared to baseline approaches on the tasks of document-level sentiment analysis by 4. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full text from SpringerLink