The QWERTY Effect on the Web

How Typing shapes the meaning of words in human-computer interaction

David García and Markus Strohmaier

Proceedings of the 25th international World Wide Web conference (WWW)

The QWERTY effect postulates that the keyboard layout influences word meanings by linking positivity to the use of the right hand and negativity to the use of the left hand. For example, previous research has established that words with more right hand letters are rated more positively than words with more left hand letters by human subjects in small scale experiments. In this paper, we perform large Thumbnail-largescale investigations of the QWERTY effect on the web. Using data from eleven web platforms related to products, movies, books, and videos, we conduct observational tests whether a hand-meaning relationship can be found in decoding text on the web. Furthermore, we investigate whether encoding text on the web exhibits the QWERTY effect as well, by analyzing the relationship between the text of online reviews and their star ratings in four additional datasets. Overall, we find robust evidence for the QWERTY effect both at the point of text interpretation (decoding) and at the point of text creation (encoding). We also find under which conditions the effect might not hold. Our findings have implications for any algorithmic method aiming to evaluate the meaning of words on the web, including for example semantic or sentiment analysis, and show the existence of “dactilar onomatopoeias” that shape the dynamics of word-meaning associations. To the best of our knowledge, this is the first work to reveal the extent to which the QWERTY effect exists in large scale human-computer interaction on the web.


Selected Media Response

Frequently Asked Questions

  • What is the QWERTY effect?
    The QWERTY effect, as postulated by Kyle Jasmin and Daniel Casasanto in 2012, is a phenomenon by which, on average, words typed with more letters from the right side of the keyboard are more positive in meaning than words typed with more letters from the left side.
  • Why is it relevant?
    We need to know the role of technology in fundamental communication processes, and the massive amounts of data created by the Web offer a chance to analyze that. Our work with the effect is an example of Computational Social Science: We test a theory from psychology against large-scale datasets of digital traces.
  • What did we find?
    We gathered data from 11 platforms in which users rated products, videos, movies, and books. We found that in most of the platforms there was a positive relationship between the ratio of right hand letters of the name of what is rated, and the average rating. We also found some evidence that the rating of a review is related to the keys used to type the text of the review.
  • How strong is the effect?
    Very weak. Interpreting effect sizes in language is not a trivial task, but we can say that our results show a soft relationship on average and definitely not a powerful effect. What we found is that the theoretical prediction is robust: It appears in multiple experiments and passes various statistical tests.
  • What causes it?
    The productive discussions at the WWW conference helped us to list four possibilities:

    • 1- The theoretical effect: The layout of the keyboard could influence meanings by associating the right hand to positive meanings. This was the main perspective in our paper, since it is motivated by previous findings in the literature.
    • 2- The reverse causation: The keyboard layout could have been biased by the emotional meanings of its designers. While this is a possibility, it might be hard to empirically test if a one time historical event was the originator of the effect.
    • 3- The phonetic confound: The layout puts letters on the right that are associated with positive meanings due to their pronunciation. Naomi Baron in New Scientist explains this possibility with an example, if the sounds of vowels are more positive and the just happen to be on the right side of the keyboard.
    • 4- The unexpected: Could there be an army of one-handed spam bots or a bias in some aggregation or search method?
  • What about left-handed people?
    Previous research indicated that left-handed people might experience the effect towards the right too, as word meanings are normative and the majority of right-handed typers would shift the positivity to the right.
  • Can you predict ratings or manipulate decisions using more right-hand letters?
    No. Our results do not have predictive or control power and we currently have no evidence that such things are possible.
  • Do your results mean that we buy more products with more right-hand letters on their name?
    No. We did not study purchase decisions, and our only analysis of sales ranks show that the effect is only present for products low in the rank.