A review of social media posts from Unicredit bank in Europe: A sentiment analysis approach

Abstract

In recent times, the increasing popularity of social media websites has provided a major source of data for mining public opinion on a variety of subjects. The opinions expressed on social media enables firms to discover individual perceived strengths and weaknesses regarding their operations as well as the products/services they offer. Twitter is one platform that gives us the opportunity to evaluate the opinions expressed by users. In this study, a dataset of tweets is downloaded from the official twitter account associated with UniCredit bank‟s main public relations outfit within the European sub-region using the Twitter API. Valence Aware Dictionary and sEntiment Reasoner (VADER), a lexicon and rule-based sentiment analysis tool that is specifically attuned to sentiments expressed on social media (e.g. Twitter), was used in conducting sentiment analysis on the tweets to examine the attitudes and feelings expressed. Using VADER to conduct sentiment analysis showed that the overall discussion was positive focusing on tweets describing UniCredit‟s engagement in corporate social responsibility activities, support for small and medium scale enterprises and business innovation. Our approach will enable the bank to gain insights on how to shape their online presence and address customer and stakeholder expectations. In theory, the study adds up to broaden the scope of online banking given the interplay of consumer sentiments via the social media channel. © 2019 Association for Computing Machinery.