Emotion is broad topic having a lot of research done on classify emotion in psycholinguistics. Words convey particular meanings and using the Tone Analyzer API to gather information from text. I will analyze a dataset using the variables emotion, language style, and social tendencies. A minor variable will be sentiment, having values of positive and negative. The main goal is to represent data about emotional trends in networks.
Emotion: Anger, Disgust, Fear, Joy, and Sadness
Language Style: Analytical, Confident, and Tentative
Social Tendencies: Openness, Conscientious, Extraversion, Agreeableness, and Emotional Range
The goal of the project is to be interactive displaying different cluster of informations. Each cluster will represent a network of sentiment. A goal is the add some animation aspect. Either a filtering field that adjusts the values displayed and a slider that can generalize or narrow the data based on user preference. The scope of the project can the data better provide an understanding of a subject:emotions, humanities, or psycholinguistics.
How can emotions be conceptualize into data?
What are the limitations to generalizing the data?
What issues arise when classifying the data?
February 27- Halfway
March 20 - Finish
Possible Data Visualization
Bubble Chart, Node Network, or Word Map
With some zoomable aspect
Cluster by word map Size shows number intensity and color by the six basic emotions. Then emotion Sentiment, confidence and language styles.
The IBM Watson™ Tone Analyzer service is based on the theory of psycholinguistics, a field of research that explores the relationship between linguistic behaviors and psychological theories.
IBM Case studies