1 Analyzing TV News

Here I will explore how different stations report on a topic with different words, and how sentiment changes with time.

2 Dataset

The TV News dataset about climate change contains almost 600 closed captioning snippets and four columns:

## Classes 'tbl_df', 'tbl' and 'data.frame':    41076 obs. of  4 variables:
##  $ station  : chr  "MSNBC" "MSNBC" "MSNBC" "MSNBC" ...
##  $ show     : chr  "Morning Meeting" "Morning Meeting" "Morning Meeting" "Morning Meeting" ...
##  $ show_date: POSIXct, format: "2009-09-22 13:00:00" "2009-09-22 13:00:00" ...
##  $ word     : chr  "the" "interior" "positively" "oozes" ...
## # A tibble: 6 x 4
##   station show            show_date           word      
##   <chr>   <chr>           <dttm>              <chr>     
## 1 MSNBC   Morning Meeting 2009-09-22 13:00:00 the       
## 2 MSNBC   Morning Meeting 2009-09-22 13:00:00 interior  
## 3 MSNBC   Morning Meeting 2009-09-22 13:00:00 positively
## 4 MSNBC   Morning Meeting 2009-09-22 13:00:00 oozes     
## 5 MSNBC   Morning Meeting 2009-09-22 13:00:00 class     
## 6 MSNBC   Morning Meeting 2009-09-22 13:00:00 raves

3 Counting totals

Find out what words are most common when discussing climate change on TV news, as well as the total number of words from each station.

3.1 Most common words when discussing climate change

## # A tibble: 3,699 x 2
##    word          n
##    <chr>     <int>
##  1 climate    1627
##  2 change     1615
##  3 people      139
##  4 real        125
##  5 president   112
##  6 global      107
##  7 issue        87
##  8 trump        86
##  9 warming      85
## 10 issues       69
## # ... with 3,689 more rows

The most common words include “issue”, “global”, and “job”.

3.2 Total Number of words from each station

## # A tibble: 3 x 2
##   station  station_total
##   <chr>            <int>
## 1 MSNBC            19487
## 2 FOX News         10876
## 3 CNN              10713

4 Sentiment analysis of TV news

4.1 Comparing TV stations

4.1.1 Which station uses the most positive or negative words?

  • How do the words used when discussing climate change compare across stations?
  • Which stations use more positive words? More negative words?

4.1.1.1 Which stations use the most negative words?

## # A tibble: 3 x 5
##   station  sentiment station_total     n percent
##   <chr>    <chr>             <int> <int>   <dbl>
## 1 MSNBC    negative          19487   526  0.0270
## 2 CNN      negative          10713   331  0.0309
## 3 FOX News negative          10876   403  0.0371

4.1.1.2 Which stations use the most positive words?

## # A tibble: 3 x 5
##   station  sentiment station_total     n percent
##   <chr>    <chr>             <int> <int>   <dbl>
## 1 FOX News positive          10876   514  0.0473
## 2 CNN      positive          10713   522  0.0487
## 3 MSNBC    positive          19487   953  0.0489

MSNBC used a low proportion of negative words but a high proportion of positive words, the reverse is true of FOX News, and CNN is middle of the pack.

4.2 Which words contribute to the sentiment scores?

It’s important to understand which words specifically are driving sentiment scores.

Proper names like Gore and Trump, which should be treated as neutral, and that “change” was a strong driver of fear sentiment, even though it is by definition part of these texts on climate change.

4.3 Word choice and TV station

Now it’s time to explore the different words that each station used in the context of discussing climate change. Which negative words did each station use when talking about climate change on the air?

Some words, like “threat” are used by all three stations but some word choices are quite different. FOX News talks about terrorism and hurricanes, while CNN discusses hoaxes.

4.4 Sentiment changes with time

Now it is time to see how sentiment is changing over time.

  • Are TV news stations using more negative words as time passes?
  • More positive words?

4.4.1 Visualizing sentiment over time

The proportion of positive words looks flat, and the proportion of negative words may be increasing.

4.4.2 Word changes over time

We can also explore how individual words have been used over time.

You can see that words like “hoax” and “denier” have been used only recently, and “warming” is decreasing in monthly uses. You can see when a hurricane was being discussed as well.