Enhanced Twofold-LDA Model for Aspect Discovery and Sentiment Classification

Enhanced Twofold-LDA Model for Aspect Discovery and Sentiment Classification

Nicola Burns (Genesys, Frimley, UK), Yaxin Bi (Ulster University, Antrim, UK), Hui Wang (Ulster University, Antrim, UK) and Terry Anderson (Ulster University, Antrim, UK)
Copyright: © 2019 |Pages: 20
DOI: 10.4018/IJKBO.2019100101
OnDemand PDF Download:
No Current Special Offers


There is a need to automatically classify information from online reviews. Customers want to know useful information about different aspects of a product or service and also the sentiment expressed towards each aspect. This article proposes an Enhanced Twofold-LDA model (Latent Dirichlet Allocation), in which one LDA is used for aspect assignment and another is used for sentiment classification, aiming to automatically determine aspect and sentiment. The enhanced model incorporates domain knowledge (i.e., seed words) to produce more focused topics and has the ability to handle two aspects in at the sentence level simultaneously. The experiment results show that the Enhanced Twofold-LDA model is able to produce topics more related to aspects in comparison to the state of arts method ASUM (Aspect and Sentiment Unification Model), whereas comparable with ASUM on sentiment classification performance.
Article Preview

Enhanced Twofold-Lda Mode

Figure 1 shows an example of the standard LDA model output, usually 30 to 100 topics manually labelled with the aspects that relate to the words in each topic. This manual work of making sense of the output can be quite time-consuming and would not be easily understood by an end user.

Figure 1.

Standard LDA output (Blei, Ng & Jordan, 2003)


Previous research using natural language processing techniques shows information in graphical form which is much more user friendly. Figure 2 shows an example of a chart comparing two digital cameras. From the chart we can clearly see that Digital Camera 1 is better in nearly every aspect and both cameras have equal positive and negative opinion on their weight. This chart means that customers no longer need to read through countless reviews to find the useful information they require. Also, the chart allows a customer to compare 2 products alongside each other.

Figure 2.

Visual comparison of two digital cameras (Liu, Hu & Cheng, 2005)


Complete Article List

Search this Journal:
Open Access Articles: Forthcoming
Volume 12: 4 Issues (2022): 3 Released, 1 Forthcoming
Volume 11: 4 Issues (2021)
Volume 10: 4 Issues (2020)
Volume 9: 4 Issues (2019)
Volume 8: 4 Issues (2018)
Volume 7: 4 Issues (2017)
Volume 6: 4 Issues (2016)
Volume 5: 4 Issues (2015)
Volume 4: 4 Issues (2014)
Volume 3: 4 Issues (2013)
Volume 2: 4 Issues (2012)
Volume 1: 4 Issues (2011)
View Complete Journal Contents Listing