Almost half of WV geotagged tweets are sent from Morgantown and Huntington

Mountain Fog is a West Virginia company, and as such we take an interest in the social media use of West Virginians. From June 9, 2015, to June 19, 2015, we sampled tweets and divided them into two categories – tweets that were sent from West Virginia and tweets that were sent from the other 49 states. Our goal was to survey the tweets between the two categories for similarities and differences.

We captured approximately 209,000 tweets, of those about 800, or about 0.40%, originated in West Virginia. (It is interesting to note that WV’s population represents 0.58% of the United States’ population according to the 2014 census.)

Tweets by City

Almost half (45.7%) of all WV geotagged tweets were sent from Morgantown and Huntington. Charleston, WV’s largest city by population, came in fourth behind Parkersburg. Perhaps the younger, student populations of Morgantown and Huntington helped contribute to the rank of each city since the cities are not ordered by population, but that’s just a hypothesis. Other areas of WV represented to a lesser degree are Wheeling and Weirton in the northern panhandle and Martinsburg in the eastern panhandle. Fewer tweets were sent from the Fairmont/Clarksburg and Beckley areas. (The West Virginia tweets that were not geotagged with a city were not considered.)

Tweets by West Virginia City


Heat map of tweets by West Virginia city

Sentiment of Tweets

Next, we looked at the sentiment of WV tweets compared to non-WV tweets. We used Idyl’s sentiment analyzer. (In case you are not familiar, Idyl is our product for performing text analysis.) We found WV tweets to be more positive than tweets from the rest of the country. 37% of WV tweets were found to have a positive sentiment compared to 31% of the tweets from the rest of the country. WV tweets were also less negative by 1%. The sentiment analysis algorithm determines whether the sentiment of a tweet is positive, negative, or neutral based on the text of the tweet. For example, the tweet “This place is great” has a positive sentiment while “This place is terrible” has a negative sentiment.

Count of WV Tweets
Count of Non-WV Tweets
Negative 172 (20.8%) 46,438 (21.07%)
Neutral 347 (41.96%) 104,308 (47.34%)
Positive 308 (37.24%) 69,604 (31.59%)

Tweet Content

As for the content of the tweets they were all over the board. There were tweets about the NBA finals, school being out, and random conversations. Perhaps a larger sample size would expose more specific topics.

Thanks for reading and stay tuned for further updates.