# BDA 2018-19 sem 2 Personality Profiling — Data 来源：https://www.kaggle.com/competitions/bda-2019-sem-2-personality-profiling/data 本地 Meta Kaggle 快照；不是本次实时页面。 # Dataset Description The YouTube Personality Dataset ------------------------------- The YouTube personality dataset consists of a collection of behavorial features, speech transcriptions, and personality impression scores for a set of 404 YouTube vloggers that explicitly show themselves in front of the a webcam talking about a variety of topics including personal issues, politics, movies, books, etc. There is no content-related restriction and the language used in the videos is natural and diverse. Detailed description -------------------- See https://www.idiap.ch/dataset/youtube-personality for complete description. **Behavioral features** Nonverbal cues were automatically extracted from the conversational excerpts of vlogs and aggregated at the video level. - Nonverbal Features from Audio: Audio cues were computed from the audio channel the toolbox developed by the [Human Dynamics group at MIT Media Lab ](http://groupmedia.media.mit.edu/data.php) and include both speaking activity and prosody cues. This is a total of 21 features. - Nonverbal Features from Video: The overall motion of the vlogger is an indicator of vloggers’ excitement and kinetic expressiveness. We computed the overall visual activity of the vlogger with a modified version of motion energy images called ”Weighted Motion Energy Images” (wMEI)]. The normalized wMEI describes the motion throughout a video as a gray-scale image, where the intensity of each pixel indicates the visual activity in it. From the normalized wMEIs, we extract statistical features as descriptors of the vlogger’s body activity such as the entropy, median, and center of gravity (in horizontal and vertical dimensions). This is a total of 4 features. **Manual transcripts** We asked a professional company to manually transcribe the audio from vlogs. The transcription corresponds to the full video duration. In total, around 28h of video were annotated. We manually anonymized the data by substituting with a ‘XXXX’ any name entities referenced by the speaker that could be use to identify the video or the vlogger, as well as references to other social media accounts. The transcriptions are provided in raw text and contain a total of ~10K unique words and ~240K word tokens. **Personality Impression Scores** The personality impressions consist of Big-Five personality scores that were collected using [Amazon Mechanical Turk](https://www.mturk.com/mturk/) and the [Ten-Item Personality Inventory ](http://homepage.psy.utexas.edu/HomePage/Faculty/Gosling/tipi%20site/tipi.htm). MTurk annotators watched one-minute slices of each vlog, and rated impressions using a personality questionnaire. The aggregated Big-Five scores are reliable with the following intra-class correlations (ICC(1,k), k=5): Extraversion (ICC = .76), Agreeableness (ICC = .64), Conscientiousness (ICC = .45), Emotional Stability (ICC = .42), Openness to Experience (ICC = .47), all significant with p < 10^-3. The personality scores are only available for 324 of the participants; the missing 80 constitute the test set. **Gender** The collection is mostly mostly balanced in gender, with 194 males (48%%) and 210 females (52%). The gender labels are also provided. Acknowledgments ----------------------- The authors