The last decade has witnessed the dramatic expansion of online social media at the global level. It is widely believed that the influence of social media is of particular importance for public and private organisations. Unfortunately, there is very limited and anecdotal evidence to show the durable influence of social media on various components and functions within organisations. To this end, this study examines the impact of social media, particularly taking the railway services in New South Wales (NSW), Australia and the Twitter platform as an illustrative example. Topic modelling and sentiment analysis techniques are employed to analyse collected tweets for evaluating the organisational performance. More precisely, five topic categories (i.e. reliability, safety, crowdedness, comfort, and convenient) are considered and relevant users' opinions are identified. Statistical results show that discussion on "opal card" is popular when travellers perceive convenient journey, while "peak" and "seat" are the biggest concerns for crowdedness. As a conclusion, the proposed work provides the flexibility and applicability for extracting and understanding complex and huge social-media data, which can in turn be used to inform organisational decision makers.
Link to publisher version (DOI)
Yang, J. & Anwar, A. Mehbub. (2016). Social media analysis on evaluating organizational performance: a railway service management. 2016 IEEE 2nd International Conference on Big Data Intelligence and Computing (DataCom 2016) (pp. 835-841). United States: IEEE.