Twitter’s social media volume does have a “significant” effect on live TV show ratings -- about a third of the time.
A new study from Nielsen looked at 221 broadcast
prime-time episodes that analyzed minute-by-minute trends. Using Nielsen’s SocialGuide social media unit, the findings reveal that the volume of tweets caused “statistically
significant” changes in live TV ratings among 29% of the episodes.
Conversely, the study also showed live TV ratings had a statistically significant impact on “related
tweets” among 48% of the episodes sampled.
Paul Donato, chief research officer of Nielsen, stated: “Using time series analysis, we saw a statistically significant causal
influence indicating that a spike in TV ratings can increase the volume of tweets, and conversely, a spike in tweets can increase tune-in.”
The highest levels of where tweets moved
the ratings needle was with competitive reality shows, which happened in 48% of episodes; comedy was at 37%; sports, 28%; and drama 18%.
Also in a release, Ali Rowghani, chief operating
officer of Twitter, said: "These results substantiate what many of our TV partners have been telling us anecdotally for years: namely, that Twitter drives tune-in, especially for live, linear
Statistical significance means the results are 95% likely to be real, but it says nothing about the size of the effect of tweets on ratings. The "effect size," however, helps determine the practical significance, that is, whether we should care (and how much). Simply knowing there is "a spike" doesn't tell us the size of the spike. Statistical significance certainly doesn't do that, but at least we're pretty sure that causation is taking place.