An analytical system for user emotion extraction, mental state modeling, and rating
作者:
Highlights:
• We estimate twelve emotions from emails - six positive and six negative.
• We propose a Markov chain model to capture the emotion dynamics.
• An algorithm rates email senders from the most emotional to the least.
• The guilty subjects expressed more positive emotions than the non-guilty.
• The guilty subjects are not more joyous than the non-guilty.’,
摘要
•We estimate twelve emotions from emails - six positive and six negative.•We propose a Markov chain model to capture the emotion dynamics.•An algorithm rates email senders from the most emotional to the least.•The guilty subjects expressed more positive emotions than the non-guilty.•The guilty subjects are not more joyous than the non-guilty.’,
论文关键词:Emotion detection,Emotion modeling,Emotion rating,Markov chain modeling,Entropy rate
论文评审过程:Received 16 February 2018, Revised 31 December 2018, Accepted 2 January 2019, Available online 23 January 2019, Version of Record 25 January 2019.
论文官网地址:https://doi.org/10.1016/j.eswa.2019.01.004