Affective Content Analysis in Comedy and Horror Videos by Audio Emotional Event Detection

Abstract

We study the problem of affective content analysis. In this paper we think of affective contents as those video/audio segments, which may cause an audience's strong reactions or special emotional experiences, such as laughing or fear. Those emotional factors are related to the users' attention, evaluation, and memories of the content. The modeling of affective effects depends on the video genres. In this work, we focus on comedy and horror films to extract the affective content by detecting a set of so-called audio emotional events (AEE) such as laughing, horror sounds, etc. Those AEE can be modeled by various audio processing techniques, and they can directly reflect an audience's emotion. We use the AEE as a clue to locate corresponding video segments. Domain knowledge is more or less employed at this stage. Our experimental dataset consists of 40-minutes comedy video and 40-minutes horror film. An average recall and precision of above 90% is achieved. It is shown that, in addition to rich visual information, an appropriate usage of special audios is an effective way to assist affective content analysis.

Mood Glove: A haptic wearable prototype system to enhance mood music in film

“…One possible approach that was considered, was to identify emotion in movie clips through using current audio-video analysis techniques to automatically classify using affective content analysis -the automated extraction of the affective content information from audiovisual signals [21]. Works in the field of automated extraction of affect in film comprise [22,23,24,25,21]. This type of approach was ruled out however.…”

Affective Recommendation of Movies Based on Selected Connotative Features

“…To date, emotional characterization of videos has been mainly used to study a narrow set of situations, such as specific sporting events as in [9] or, most frequently, movies that belong to a particular genre such as horror movies, as in [10]. Extending this approach, Xu et al [11] described emotional clustering of films for different genres, using averaged values of arousal and valence deduced from video parameters.…”

“…AQ:3= Please provide page range in Refs. [9], [10], [16], [20], [22], [23], [33], [35], [38], [44], [46], [47].…”

A Connotative Space for Supporting Movie Affective Recommendation

“…To date, emotional characterization has been mainly used to study a narrow set of situations, like specific sport events as in [8] or movies that belong to a particular genre, for example horror movies, as in [9].…”