Abstract
Do people learn about the political world through online media? We
address this question by developing different exogenous measures of
media exposure, drawing on three months of web-tracking data from five
democracies. Our analysis distinguishes between visits to general news
domains and visits to politically or content-specific articles, identified
using machine learning techniques. We evaluate these measures through
multiple approaches, including their ability to significantly predict political
knowledge. To deepen our understanding, we analyze knowledge gains
during a major, unexpected news event—the 2022 Russian invasion of
Ukraine—using observed media exposure measures varying in
granularity. Our findings underscore the importance of granularity: visits
and time spent on Ukraine-related articles emerge as the only significant
predictor of surveillance knowledge, while broader measures, such as
domain-level visits, show no significant impact when controlling for self-
reported exposure and other key predictors. We conclude by discussing
the substantive and methodological implications of these results.
address this question by developing different exogenous measures of
media exposure, drawing on three months of web-tracking data from five
democracies. Our analysis distinguishes between visits to general news
domains and visits to politically or content-specific articles, identified
using machine learning techniques. We evaluate these measures through
multiple approaches, including their ability to significantly predict political
knowledge. To deepen our understanding, we analyze knowledge gains
during a major, unexpected news event—the 2022 Russian invasion of
Ukraine—using observed media exposure measures varying in
granularity. Our findings underscore the importance of granularity: visits
and time spent on Ukraine-related articles emerge as the only significant
predictor of surveillance knowledge, while broader measures, such as
domain-level visits, show no significant impact when controlling for self-
reported exposure and other key predictors. We conclude by discussing
the substantive and methodological implications of these results.
| Original language | English |
|---|---|
| Journal | The Public Opinion Quarterly |
| Publication status | Accepted/In press - 6 Jun 2025 |
Keywords
- news exposure
- web-tracking data
- exogenous measures
- computational methods
- Ukraine war
- surveillance knowledge