What are they really saying?

Read Between the Lines

wordcloud

Source information in MS Skydrive

Nerd Corner

It won’t take long for you to realise the importance marketing plays in the milkround process as each firm seeks to differentiate themselves from the pack. One of the core elements of each firm’s milkround campaign is their graduate brochure so I thought it would be a good idea to see what message are each firm trying to get across from their brochure. I have outlined below a summary of the steps I used to create this graphic;

  • I used Python (programming language) and Inkscape (a free open source software for graphic design type projects) to create the graphic;
  • I downloaded each of the graduate brochures and scraped all the text from them using python. I then cleaned this up (removing punctuation and stop words);
  • I then created a text file with the most popular words from each brochure (the number of words chosen depended on the size of the brochure as some smaller brochures would have few words repeated frequently);
  • These text files were then loaded into Tagxedo (online word cloud generator) to create each word cloud;
  • The clouds are then pasted into Inkscape and formatted; and
  • Finally, MS SkyDrive is a nice platform to store all the source links which allows them to be easily accessed by any user if required;