Researchers now study Twitter for the next major advancement in social media: It’s called “influence maximization”—which is identifying a fixed number of influencers whose opinions can sway the biggest audiences.
At stake is how companies and marketers, under a budget, seek a specific number of influencers with the biggest impact on public opinion. Their number could be 10 or less.
Because current models for measuring social media influence totally ignore the long-term influence effects of dynamic interactions, researchers are developing a better model (login may be required for full text) that includes that interaction data for better results.
Researchers have developed a new model and an algorithm to track and understand opinions on a specific topic by examining users’ dynamic interactions on Twitter.
Researchers develop first ‘interpersonal influence’ model in quest for influence maximization
They call it a “temporal influence model,” and they contend it’s the first of its kind.
The algorithm is designed to predict future opinions of social media users, especially those users with a high diversity of opinions.
The interpersonal influence learned by the algorithm can be used to find those social media influencers whose reach is the greatest on a network. It’s the most important part of solving influence maximization, they say.
Read research here (login may be required for full text)
“To the best of our knowledge, our work is the first to model interpersonal influence as the continuous impact of opinion behaviors using real-world social media data,” their study says.
Here is a short Q&A with researchers Chengyao Chen and Wenjie Li of Hong Kong Polytechnic University, Dehong Gao of Alibaba Group, and Yuexian Hou of Tianjin University, who have authored a new study about what they assert is the next big thing in social media.
What may surprise you is whom they call a role model in this emerging trend.
Is influence maximization the next big thing for social media and their metrics?
Of course, influence maximization is the next big thing for social media. Engaging the influencers for marketing has become one of the most effective ways to promotion. Influence maximization solves an important problem in influencer marketing, which is how to balance the budget and the marketing results. The metrics of influence maximization include the final range over the social network that the influence can reach.
Why is this subject important and being studied?
Currently, social media has already become one of the largest platforms for marketing and advertising. Compared with traditional advertisements, people are more likely to trust a recommendation from a person they contact every day through social channels. In fact, according to one recent marketing survey, 71% of consumers said they are more likely to make a purchase based on a personal recommendation online. It is important to engage the social media influencers in the marketing campaigns by publishing their messages that promote the company brands or products.
Explain influence maximization.
Usually, the budget of companies is limited, and they can only afford the cost of a specific number of influencers (e.g., 10 social media users). In this situation, we can define the problem as influence maximization, which is to find the specific set of users whose message can be received by the largest number of users on social media.
For influencers on Twitter, Facebook, Instagram, LinkedIn, what are the takeaways from your findings?
Find your expert area.
According to our study, the influence varies greatly for the same user on different topics. Find your expert area and gradually accumulate your influence in this area.
Share valuable information such as facts and avoid the emotional expressions. On social media, people usually use many emotional words such as “woo”, “wow” or some emoticons “o_o”. However, based on our latest study, if you use heavily emotional expressions, it is more difficult to win trust from others.
Who is a role model for influence maximization?
We would say Michelle Phan (Twitter account: @michellephan. Editor’s note: Her image is atop this article). She focuses on the area of beauty and posts videos to teach people everything about makeup. Her interesting and professional videos attract many people to follow her and share her videos with their friends. In this way, Michelle can disseminate the information to her followers who then spread her videos to other people who may not follow her.
Read more about their work in the May/June 2017 issue of IEEE Intelligent Systems. Their research was supported by the Research Grants Council of Hong Kong, National Natural Science Foundation of China, and Hong Kong Polytechnic University.
Read the research (login may be required for full text)
Read more about Twitter in Computer Society articles and research
Login may be required for full text.
- User Anonymity on Twitter
- Identification of Extremism on Twitter
- Predicting Twitter Hashtags Popularity Level
- Palantir: Crowdsourced Newsification Using Twitter
- Detecting Jihadist Messages on Twitter
- Characterization of Football Supporters from Twitter Conversations
- Reverse engineering socialbot infiltration strategies in Twitter
- Misinformation Propagation in the Age of Twitter
- Finding street gang members on Twitter
- Prevalence and Attitudes about Illicit and Prescription Drugs on Twitter
About Michael Martinez
Michael Martinez, the editor of the Computer Society’s Computer.Org website and its social media, has covered technology as well as global events while on the staff at CNN, Tribune Co. (based at the Los Angeles Times), and the Washington Post. He welcomes email feedback, and you can also follow him on LinkedIn.
About Lori Cameron
Lori Cameron is a Senior Writer for the IEEE Computer Society and currently writes regular features for Computer magazine, Computing Edge, and the Computing Now and Magazine Roundup websites. Contact her at firstname.lastname@example.org. Follow her on LinkedIn.