Browsing by Author "Walker, Lorna"

Now showing 1 - 2 of 2
  • Thumbnail Image
    ItemOpen Access
    Antecedents of retweeting in a (political) marketing context
    (Wiley, 2017-02-13) Walker, Lorna; Baines, Paul R.; Dimitriu, Radu; Macdonald, Emma K.
    Word of mouth disseminates across Twitter by means of retweeting; however the antecedents of retweeting have not received much attention. This study uses the CHAID decision tree predictive method (Kass, 1980) with readily available Twitter data, and manually coded sentiment and content data, to identify why some tweets are more likely to be retweeted than others in a (political) marketing context. The analysis includes four CHAID models: (i) using message structure variables only, (ii) source variables only, (iii) message content and sentiment variables only and (iv) a combined model using source, message structure, message content and sentiment variables. The aggregated predictive model correctly classified retweeting behavior with a 76.7% success rate. Retweeting tends to occur when the originator has a high number of Twitter followers and the sentiment of the tweet is negative, contradicting previous research (East, Hammond, & Wright, 2007; Wu, 2013) but concurring with others (Hennig-Thurau, Wiertz, & Feldhaus, 2014). Additionally, particular types of tweet content are associated with high levels of retweeting, in particular those tweets including fear appeals or expressing support for others, whilst others are associated with very low levels of retweeting, such as those mentioning the sender’s personal life. Managerial implications and research directions are presented. The study makes a methodological contribution by illustrating how CHAID predictive modelling can be used for Twitter data analysis and a theoretical contribution by providing insights into why retweeting occurs in a (political) marketing context.
  • Thumbnail Image
    ItemOpen Access
    What factors influence whether politicians’ tweets are retweeted? Using CHAID to build an explanatory model of the retweeting of politicians’ tweets during the 2015 UK General Election campaign
    (Cranfield University, 2016-09) Walker, Lorna; Baines, Paul R.
    Twitter is ever-present in British political life and many politicians use it as part of their campaign strategies. However, little is known about whether their tweets engage people, for example by being retweeted. This research addresses that gap, examining tweets sent by MPs during the 2015 UK General Election campaign to identify which were retweeted and why. A conceptual model proposes three factors which are most likely to influence retweets: the characteristics of (1) the tweet’s sender, (2) the tweet and (3) its recipients. This research focuses on the first two of these. Content and sentiment analysis are used to develop a typology of the politicians’ tweets, followed by CHAID analysis to identify the factors that best predict which tweets are retweeted. The research shows that the characteristics of tweet and its sender do influence whether the tweet is retweeted. Of the sender’s characteristics, number of followers is the most important – more followers leads to more retweets. Of the tweet characteristics, the tweet’s sentiment is the most influential. Negative tweets are retweeted more than positive or neutral tweets. Tweets attacking opponents or using fear appeals are also highly likely to be retweeted. The research makes a methodological contribution by demonstrating how CHAID models can be used to accurately predict retweets. This method has not been used to predict retweets before and has broad application to other contexts. The research also contributes to our understanding of how politicians and the public interact on Twitter, an area little studied to date, and proposes some practical recommendations regarding how MPs can improve the effectiveness of their Twitter campaigning. The finding that negative tweets are more likely to be retweeted also contributes to the ongoing debate regarding whether people are more likely to pass on positive or negative information online.