Figure 3. Examples of tweets classified as ridicule. From: Machine Learning, Sentiment Analysis, and Tweets: An Examination of Alzheimer’s Disease Stigma on Twitter J Gerontol B Psychol Sci Soc Sci. 2017;72(5):742-751. doi:10.1093/geronb/gbx014 J Gerontol B Psychol Sci Soc Sci | © The Author 2017. Published by Oxford University Press on behalf of The Gerontological Society of America. All rights reserved. For permissions, please e-mail: journals.permissions@oup.com.
Figure 2. Example of a tweet that is informative (A) and a tweet that is a joke and ridiculing (B). From: Machine Learning, Sentiment Analysis, and Tweets: An Examination of Alzheimer’s Disease Stigma on Twitter J Gerontol B Psychol Sci Soc Sci. 2017;72(5):742-751. doi:10.1093/geronb/gbx014 J Gerontol B Psychol Sci Soc Sci | © The Author 2017. Published by Oxford University Press on behalf of The Gerontological Society of America. All rights reserved. For permissions, please e-mail: journals.permissions@oup.com.
Figure 1. Example of web interface used in manual coding. From: Machine Learning, Sentiment Analysis, and Tweets: An Examination of Alzheimer’s Disease Stigma on Twitter J Gerontol B Psychol Sci Soc Sci. 2017;72(5):742-751. doi:10.1093/geronb/gbx014 J Gerontol B Psychol Sci Soc Sci | © The Author 2017. Published by Oxford University Press on behalf of The Gerontological Society of America. All rights reserved. For permissions, please e-mail: journals.permissions@oup.com.
Figure 4. Percentage of machine coded tweets representing each dimension by ridicule. Note. Percentages for each dimension are of a total of N = 6,583 ridicule tweets for the light bars and of a total of N = 31,150 overall tweets for the dark bars. 21.13% of all tweets were classified as ridicule by the machine learning model. From: Machine Learning, Sentiment Analysis, and Tweets: An Examination of Alzheimer’s Disease Stigma on Twitter J Gerontol B Psychol Sci Soc Sci. 2017;72(5):742-751. doi:10.1093/geronb/gbx014 J Gerontol B Psychol Sci Soc Sci | © The Author 2017. Published by Oxford University Press on behalf of The Gerontological Society of America. All rights reserved. For permissions, please e-mail: journals.permissions@oup.com.