A Database For Emotional Interactions Of The Elderly

Emotional interaction plays an important role in human-computer interaction domains. One of the major limitations in the study of emotion interaction is the lack of databases. This paper describes a database for emotion interactions of the elderly. The database was collected with audio and video from sixteen actors (8 female and 8 male) in daily conversations of TV series, which covers seven type emotions, namely, anger, boredom, happiness, sadness, surprise, neutrality and disgust. The database consists of 810 speech-video excerpts from 118 conversations. Emotion annotations were evaluated by 18 participants (10 men and 8 women). In addition, this databases record the transitions of actors' emotion in daily conversations.