Sentiment Analysis in Corporate Legitimacy

Introduction

Sentiment analysis entails the task and process of automatically determining from the text the attitude, emotions and other affectual state of the author regarding a subject (Mohammad, 2016; Liu, 2012). In context, Maas et al. (2012) and Cambria (2016) viewed sentimental analysis as an approach of identifying and extracting subjective information useful in conceptualizing social sentiment of services, branding, and organization itself by following conversations on online platforms. Complexity and competition in contemporary business environment has forced organizations to integrate structure capturing explicitly the opinions and behaviour of current and potential consumers that include anticipated behavioural and opinion change hence the significance of analysis of online data collected on daily basis (Ravi, & Ravi, 2015; Alessia et al., 2015). These provide great insight and anticipated change in behaviour and opinion concerning a product, services, or an organizations hence help planning and restructuring values and approaches. The study conducted takes into account 50 tweets about Wells Fargo and Bank of America with specific regard to their Corporate Social Responsibilities (CSR) indulgences in the disciplines of Education, Training Immigration and many others. This was in the aim to not only to analyse the emotional state of the author of these tweets but also to identify a common pattern that may effectively point to the corporate legitimacy of the companies in the public’s eye.

Wells Fargo

In 27 out of 50 instances, the analysis of the tweets from the millennials and the LIWC compared highlighted 54% accuracy in the sentimental analysis structures used in the analysis. While this consistencies have been experienced in instances of positive, negative, as well as neutral measures, the general outlook is a positive response highlighting considerable levels of legitimacy in Wells Fargo corporate Social Responsibility indulgences. 25 of the posts were assigned positive measures by the millennials while 30 were flagged as positive comments towards the companies CSR endeavours by the LIWC this coupled with the neutrally measured tweets against the negative ones highlight wells Fargo to exhibit a considerable level of legitimacy. While the millennial identified 15 tweets with negatively inclined messages, LIWC identified only 7 tweets under the negative measure.

Bank of America

According to the LIWC benchmark 31 out of 50 tweets on the CSR activities of Bank of America received a positive measure, highlighting a strong level of legitimacy in their actions. This is further strengthened by 22 out of 50 of the tweets being valued by the millennials to have a positive measure. Despite the low number of tweets approved by the millennials as positive, a considerable number of the tweets (18) are considered neutral tweets by the millennials leaving only 10 tweets that had a negative measure. This further accentuates the legitimacy of the company. It is comparable to the LIWC which also registers 11 neutral tweets and only 8 negative ones.

Given the tallied outcomes, in 37 instances out of the 50 available, the LIWC was in tandem with the millennials analysis of the tweets suggesting a 74% accuracy which further confirms Bank of America to be a legitimate financial institution in the Americans public eye. Despite the discrepancy in the accuracy level in the Bank of America and Wells Fargo analysis, it is quite clear from the sentimental analysis that both financial institutions are largely considered legitimate organizations within the society. Bank of America however, registered a higher accuracy in analysis between the millennials and the LIWC analysis and also had most of the tweets related to it identified as positive and neutral tweets by both the millennials and the LIWC, and as such it can be assumed to be a more legitimate organization than Wells Fargo.

References

Alessia, D., Ferri, F., Grifoni, P., & Guzzo, T. (2015). Approaches, tools and applications for sentiment analysis implementation. International Journal of Computer Applications, 125(3).

Cambria, E. (2016). Affective computing and sentiment analysis. IEEE Intelligent Systems, 31(2), 102-107.

Liu, B. (2012). Sentiment analysis and opinion mining. Synthesis lectures on human language technologies, 5(1), 1-167.

Liu, B. (2015). Sentiment analysis: Mining opinions, sentiments, and emotions. Cambridge University Press.

Maas, A. L., Daly, R. E., Pham, P. T., Huang, D., Ng, A. Y., & Potts, C. (2011, June). Learning word vectors for sentiment analysis. In Proceedings of the 49th annual meeting of the association for computational linguistics: Human language technologies-volume 1 (pp. 142-150). Association for Computational Linguistics.

Ravi, K., & Ravi, V. (2015). A survey on opinion mining and sentiment analysis: tasks, approaches and applications. Knowledge-Based Systems, 89, 14-46.