Universal Appeal. The subject of widely popular micro-video cannot be something which only a small group of people will appreciate or understand. Therefore, the topics and objects contained in micro-videos should be something common so that to be interpreted the same way across people and cultures. For this characteristic, we extracted Sentence2Vector feature of micro-video's textual description and cnn feature of visual content.

Emotional Content. People are naturally drawn to things that arouse their emotions. Micro-videos showing funny animals or lovely babies make people feel urge to share them to express the same emotions. As a result, micro-videos that are highly emotional are more likely to be shared. Therefore, we extracted textual sentiment, visual sentiment features for each video as well as several acoustic features, which is widely used in emotion recognition in speech.

High Quality and Aesthetic Design. When people share information on social networks, people are actually showing a little piece of themselves to their audience. Therefore, high quality and aesthetic design of the content, which could reflect the taste of people, is another important characteristic of popular micro-video. Color histogram, aesthetic feature and visual quality feature were extracted for this characteristic. In addition, the acoustic features we extracted are frequently used in music modeling, which could help to detect music in the audio track of micro-videos.