Next Article in Journal
Noise Sources and Control, and Exposure Groups in Chemical Manufacturing Plants
Previous Article in Journal
A Comparison of Different District Integration for a Distributed Generation System for Heating and Cooling in an Urban Area
Article

Incorporating Word Significance into Aspect-Level Sentiment Analysis

1
School of Information and Software Engineering, University of Electronic Science and Technology of China, Xiyuan Ave, West Hi-Tech Zone, Chengdu 611731, Sichuan, China
2
Department of Information Technology, South Eastern Kenya University, 170, Kitui 90200, Kenya
*
Author to whom correspondence should be addressed.
Appl. Sci. 2019, 9(17), 3522; https://doi.org/10.3390/app9173522
Received: 28 July 2019 / Revised: 16 August 2019 / Accepted: 20 August 2019 / Published: 27 August 2019
(This article belongs to the Section Computing and Artificial Intelligence)
Aspect-level sentiment analysis has drawn growing attention in recent years, with higher performance achieved through the attention mechanism. Despite this, previous research does not consider some human psychological evidence relating to language interpretation. This results in attention being paid to less significant words especially when the aspect word is far from the relevant context word or when an important context word is found at the end of a long sentence. We design a novel model using word significance to direct attention towards the most significant words, with novelty decay and incremental interpretation factors working together as an alternative for position based models. The interpretation factor represents the maximization of the degree each new encountered word contributes to the sentiment polarity and a counter balancing stretched exponential novelty decay factor represents decaying human reaction as a sentence gets longer. Our findings support the hypothesis that the attention mechanism needs to be applied to the most significant words for sentiment interpretation and that novelty decay is applicable in aspect-level sentiment analysis with a decay factor β = 0.7 . View Full-Text
Keywords: aspect-level sentiment analysis; attention mechanism; novelty decay; incremental interpretation; stretched exponential law aspect-level sentiment analysis; attention mechanism; novelty decay; incremental interpretation; stretched exponential law
Show Figures

Figure 1

MDPI and ACS Style

Mokhosi, R.; Qin, Z.; Liu, Q.; Shikali, C. Incorporating Word Significance into Aspect-Level Sentiment Analysis. Appl. Sci. 2019, 9, 3522. https://doi.org/10.3390/app9173522

AMA Style

Mokhosi R, Qin Z, Liu Q, Shikali C. Incorporating Word Significance into Aspect-Level Sentiment Analysis. Applied Sciences. 2019; 9(17):3522. https://doi.org/10.3390/app9173522

Chicago/Turabian Style

Mokhosi, Refuoe, ZhiGuang Qin, Qiao Liu, and Casper Shikali. 2019. "Incorporating Word Significance into Aspect-Level Sentiment Analysis" Applied Sciences 9, no. 17: 3522. https://doi.org/10.3390/app9173522

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop