Week 7 Readings and Homework

READ (Several of these are short):

Hatfield, Elaine, John T. Cacioppo, and Richard L. Rapson. "Emotional contagion." Current directions in psychological science 2, no. 3 (1993): 96-100.  EmotionalContagion.pdf Download EmotionalContagion.pdf

Kramer, Adam DI, Jamie E. Guillory, and Jeffrey T. Hancock. "Experimental evidence of massive-scale emotional contagion through social networks." Proceedings of the National Academy of Sciences 111, no. 24 (2014): 8788-8790. EmotionalContagion_SocialNetwork.pdf Download EmotionalContagion_SocialNetwork.pdf

Lanier, Jaron.  "Should Facebook Manipulate Users?"  https://www.nytimes.com/2014/07/01/opinion/jaron-lanier-on-lack-of-transparency-in-facebook-study.html Links to an external site.

Crawford, Kate. "The Test We Can and Should Run on Facebook" https://www.theatlantic.com/technology/archive/2014/07/the-test-we-canand-shouldrun-on-facebook/373819/ Links to an external site.

boyd, danah. "Untangling research and practice: What Facebook’s “emotional contagion” study teaches us." Research Ethics 12.1 (2016): 4-13.  https://journals.sagepub.com/doi/pdf/10.1177/1747016115583379 Links to an external site.

READ (but it's OK to skim all of the machine learning/technical details if you don't get those):

Benitez-Quiroz, Carlos F., Ramprakash Srinivasan, and Aleix M. Martinez. "Facial color is an efficient mechanism to visually transmit emotion." Proceedings of the National Academy of Sciences 115.14 (2018): 3581-3586. Benitez-Quiroz-etal-2018-Emotion-in-Facial-Color.pdf Download Benitez-Quiroz-etal-2018-Emotion-in-Facial-Color.pdf

Pang, Bo, Lillian Lee, and Shivakumar Vaithyanathan. "Thumbs up? Sentiment classification using machine learning techniques." arXiv preprint cs/0205070 (2002).  Pang-etal-2002-Thumbs Up Sentiment Classification Using ML.pdf Download Pang-etal-2002-Thumbs Up Sentiment Classification Using ML.pdf

Felbo, B., Mislove, A., Søgaard, A., Rahwan, I., & Lehmann, S. (2017). Using millions of emoji occurrences to learn any-domain representations for detecting sentiment, emotion and sarcasm. arXiv preprint arXiv:1708.00524. Felbo-etal-2017-Emoji-Sentiment.pdf Download Felbo-etal-2017-Emoji-Sentiment.pdf

EXPLORE and WRITE:

1) Take 5mins and see how easy/hard it is to label some sentiment data using ONLY ONE of the two forms below.  Both are anonymous. 

If the number of the day you were born on is an odd number, e.g. April 13, label these sentiments: https://forms.gle/NM3X62DiJ3GAvrGHA Links to an external site. 

Otherwise, the number of the day you were born on was even, e.g.. May 24, so label these sentiments: https://forms.gle/WUfuwuUozaU5cxXP6 Links to an external site. 

Links to an external site.

2) Play with Deepmoji 5-10mins; you don't have to participate in their COUHES study (totally optional) but at least play with the interface at https://deepmoji.mit.edu/.  Try at least 4 very different kinds of emotions, with multiple ways of expressing each (including several subtle ways).  Which 4 emotions did you try?  Clip and show your input text and "best" answer and your "worst" answer for each of the four emotions.  (Give eight clips total)

3) Pick one of these two sides and write a couple paragraphs arguing your side:  

(a) It's NOT fine for Facebook (and companies like them) to run studies that manipulate their users' emotions

(b) It's fine for Facebook (and companies like them) to run studies that manipulate their users' emotions

4)  Pick one of these two sides and write a couple paragraphs arguing your side:  

(a) Cameras+AI should be prohibited from reading any emotional information about people in public places.

(b) Cameras+AI should not be prohibited from reading emotional information about people in public places.

5) Noah Jones will be giving us an introduction to sentiment analysis for the second half of class.  Formulate one question here for him, showing you are familiar with the main challenges and progress described in the Pang and Felbo papers.