Dhaoui, C., Webster, C. and Tan, L. (2017). Social media sentiment analysis: lexicon versus machine learning. Journal of Consumer Marketing, 34(6), pp.480-488.

From Digital Culture & Society

The article chosen for this review, “Social media sentiment analysis: lexicon versus machine learning”, aims to increase the reach of digital marketers in regard to consumer’s opinions towards different products, services and brands in the online sphere. In order to do so, the authors analyzed two different techniques that classify sentiments of social media comments. The authors used comments taken from Facebook pages of brands, in order to compare a lexicon based approach and a machine learning based approach to sentiment analysis. A lexicon based approach considers the connotation around the semantic orientation, while a machine based approach uses algorithms created for language processing; manually inputted data that was originally classified by a human is the base point for sentiment analysis with this technique. The author asked three research questions at the beginning of the article;

1. The first research question looked at whether the two sentiment analysis techniques outlined above are appropriate for the analysis of social media conversations; the authors were basically asking if those two tests were reliable in the first place. The authors found that both tests provided the same output of classification when applied to positive comments, and negative comments were positively correlated as well, just not as strong identification as the positive comments.
2. The second research question asked how the two techniques differed in their approach to social media conversation analysis, and provided details on how to decide which approach to use in a particular situation. Machine learning approaches tend to be stronger in their identification abilities, but machine learning approaches would not be possible without the data accrued from the lexicon based approach. The authors proposed a combination of the two approaches to be ideal, and using manually captured data from a lexicon approach to begin the machine learning data set training would be best suited for general usage of the sentiment analysis techniques.
3. Finally, the author questioned if the combination approach actually improves the overall accuracy of sentiment analysis while looking at social media conversations. The results of this article indicated that both techniques are similar in their output of different classifications, and that the two approaches are stronger for identifying and classifying positive comments rather than negative comments. This is because not only do machines find it difficult to analyze sarcasm, but humans do as well while manually classifying data through the lexicon approach. The authors still discovered that the two approaches are stronger when used together, and propose a combined approach to be the ideal way to do sentiment analysis.

This paper contributed a large degree of its findings from the research; beginning with the empirical tests of two sentiment analysis approaches that are prominent within the field. These two approaches, lexicon based and machine based, have different approaches but similar performance. The authors also provided evidence towards the idea that a combination of the two approaches has more precision than either on its own. The authors gave credence to tools that provide options for attempting to analyze the sheer amount of data that is spewed out on social media sites. These findings will help improve the accuracy of target markets and target advertising for digital marketers, leading to more personalized and target messages for consumers.

Significant improvements were shown as well, in regard to these two classification techniques, which was not originally supported by previous literature. The authors reported that this research study, and others based on sentiment analysis before it, are negatively impacted due to limitations on the assessment of only text-based messages in automated sentiment analysis. The author proposes research into the sentiment analysis of other content, such as images and videos. That is the future of sentiment analysis; these techniques, or others grown from the base of these groundbreaking tools, will be used on every piece of data floating through the internet. Comments, videos, pictures and other forms of communication will be analyzed thoroughly in order to provide you with advertisements and other interesting data that a computer algorithm says that you will enjoy.

Megan McGuire