Features Professional Education & Research

Political polarisation in the new media age

By : Michelle Liu

Public opinion has become more polarised in an age defined by the integration of digital and social media in people’s daily lives.

In response, a digital and social media research team at CityU has proposed new ways of understanding public opinion by adopting a big data-based approach to online textual mining.

Dr Chris Shen Fei, Associate Professor in the Department of Media and Communication, launched the Hong Kong Online Public Opinion Data Mining Project with his team in 2018.

The project uses automatic textual analysis to understand online public opinion on issues across five thematic domains, including public figure popularity, organisation popularity, public attitudes toward the mainland, social issues and corporate image, explains Dr Shen, who specialises in the social and political impacts of new media technologies.

The team has identified 12 typical online platforms as data sources, including discussion forums and news media sites, and performed data crawling, data cleaning, tokenisation, lexicon development and data analysis to transform unstructured data into visualised patterns of public opinion over time in Hong Kong. The time span of the data is from the original data that can be retrieved from each platform until the end of 2019.

“We are living during a time in which timely and comprehensive understanding of public opinion is greatly needed. Traditional polling has many limitations, such as high costs and respondents’ sensitivity to how questions are worded, but big data provides us with a new direction for public opinion analysis by taking full advantage of people’s openly shared expressions online,” says Dr Shen.

LikesThe project has found that online political discussions over the past several years have become more negative in tone, with hate speech commonly seen on social media platforms.

“Hong Kong’s problem does not lie in ideological differences among residents; rather, the major issue is that people of different political stripes view each other as enemies,” Dr Shen says.

“While it is undesirable and even impossible to eliminate political differences, reducing political affective polarisation is one of the greatest tasks faced by society. Political affective polarisation means the tendency of people to dislike or distrust others simply because of a different political stance,” Dr Shen adds.

The team’s research suggests that communication and discussion without a proper design and an experienced moderator can easily lead to the proliferation of extreme ideas and negative emotions.

Dr Shen conducted two pilot experiments last year to explore the impacts of “deliberation” and “causal discussion” as a means of reducing political polarisation in Hong Kong.

In Study 1, people holding opposing views on Article 23 of the Hong Kong Basic Law were invited to participate in a 90-minute discussion. They were randomly assigned into one of two groups: deliberation or casual discussion. The deliberation group received an information booklet and were asked to follow some rules strictly, such as showing respect for others and trying their best to understand others’ opinions fairly.

In Study 2, video recordings from Study 1 were presented to another two groups of participants. One group watched the deliberation video and the other group watched the causal discussion video. Pre- and post-test surveys were conducted in both experiments.

The experiments found that both deliberation and casual discussion had mixed effects on reducing political polarisation. In Study 1, while issue attitude and issue polarisation remained largely unchanged, people’s attitude towards those holding opposing views became more favourable, and consequently affective polarisation was reduced. The average rating toward opposition camps increased from 3.92 to 6.08. Such effects were more prominent in the deliberation group than in the casual discussion group. While in Study 2, people who watched others participating in deliberation and causal discussion showed similar effects, but to a much smaller extent.

Dr Chris Shen Fei Dr Chris Shen Fei “The media with particular political inclinations in Hong Kong often portray people holding different political views as unscrupulous, ignorant or uncivil. Exposure to these media in the long run will ossify inaccurate and dehumanising stereotypes toward people with different opinions. But participation in face-to-face dialogue will show that people holding opposing views are just normal people with their own dignity and integrity,” Dr Shen says.

Dr Shen hopes his research can benefit decision-making by policymakers, the public and the academic community in the long run. He recommends non-governmental organisations set up more political dialogue programmes to facilitate communications among the public. A more realistic approach is to identify a few communities as field experiment settings and conduct longitudinal studies about the long-term effect of implementing community-based political dialogues programmes.

Recently Dr Shen has been conducting research into whether third party fact-checkers on social media platforms can reduce affective polarisation by promoting mutual understanding and respectful discourse. His project has received funding from the Facebook Research Award 2020.

Home

Acknowledgements