Discovering Temporal Retweeting Patterns for Social Media Marketing Campaigns

Abstract

Social media has become one of the most popular marketing channels for many companies, which aims at maximizing their influence by various marketing campaigns conducted from their official accounts on social networks. However, most of these marketing accounts merely focus on the contents of their tweets. Less effort has been made on understanding tweeting time, which is a major contributing factor in terms of attracting customers' attention and maximizing the influence of a social marketing campaign. To that end, in this paper, we provide a focused study of temporal retweeting patterns and their influence on social media marketing campaigns. Specifically, we investigate the users' retweeting patterns by modeling their retweeting behaviors as a generative process, which considers temporal, social, and topical factors. Moreover, we validate the predictive power of the model on the dataset collected from Sina Weibo, the most popular microblog platform in China. By discovering the temporal retweeting patterns, we analyze the temporal popular topics and recommend tweets to users in a time-aware manner. Finally, experimental results show that the proposed algorithm outperforms other baseline methods. This model is applicable for companies to conduct their marketing campaigns at the right time on social media.

Mining Features Associated with Effective Tweets

“…The study of what features are associated with a "viral" tweet has attracted much attention in the recent years, mostly with regard to the retweeting behavior. There has been in-depth analysis on certain dimensions of tweets, such as sentiment analysis [16]- [19], Tsur et al [20] on multiple features of hashtags, Naveed et al [21] on tweet content such as emoticons, Dabeer et al [22] and Liu et al [23] on timing of tweets, and so on. The correlation between these features and the number of retweets has been studied using conventional statistical methods such as Principal Component Analysis [24], generalized linear model [25] and so on.…”

Flexible Query Answering Systems 2015

“…As mentioned above, the timeslot was set to 48 corresponding to different hours in weekdays and weekends. This partition standard is similar to that in [14] where it was applied to the retweeting time in Twitter. Unlike retweeting patterns, consumers' shopping behaviors may not be so sensitive to whether the day is weekday or weekend.…”

“…The size of recommendation set K ranged from 5 to 15, that is, K ∈ {5, 6,7,8,9,10,11,12,13,14 where S is the collection of records in test set and AP (s) @K can be computed by:…”

The Story of Goldilocks and Three Twitter’s APIs: A Pilot Study on Twitter Data Sources and Disclosure

“…Further, we observed more than half the sample of user accounts related to e-cigarette marketing from the Streaming API have been deleted or suspended since the time of data retrieval. We do not know how influential those accounts and tweets were in the promotion of that particular product, but we do know that most tweets are viewed as they stream or relatively close to the time they are posted [32][33][34] and that online information exposure influences offline behavior [35][36][37]. Thus, it is possible that tweets that were deleted after they were originally posted (and captured by the Streaming API) influenced the behavior of a large audience prior to deletion.…”