In this chapter, we focus on the detection of sentiment strength values for a given document. A convolution-based model is proposed to encode semantic and syntactic information as feature vectors, which has the following two characteristics: (1) it incorporates shape and morphological knowledge when generating semantic representations of documents; (2) it divides words according to their part-of-speech (POS) tags and leams POS-level representations for a document by convolving grouped word vectors. Experiments using six human-coded datasets indicate that our model can achieve comparable accuracy with that of previous classification systems and outperform baseline methods over correlation metrics.
|Title of host publication||Multimodal analytics for next-generation big data technologies and applications|
|Editors||Kah Phooi SENG, Li-minn ANG, Alan Wee-Chung LIEW, Junbin GAO|
|Place of Publication||9783319975979|
|Publisher||Springer International Publishing AG|
|Number of pages||19|
|Publication status||Published - 2019|
RAO, Y., XIE, H., WANG, F. L., POON, L. K. M., & ZHU, E. (2019). Hybrid feature-based sentiment strength detection for big data applications. In K. P. SENG, L. ANG, A. W-C. LIEW, & J. GAO (Eds.), Multimodal analytics for next-generation big data technologies and applications (pp. 73-91). Springer International Publishing AG. https://doi.org/10.1007/978-3-319-97598-6_4