教育培训类微信视频号直播带货违法监测预警数据
收藏资源简介：
对采集的微信视频号平台带货品类为教育培训类的达人直播视频内容进行转译分析，对达人口播语言内容进行处理、分析，根据达人在直播过程中对预先设置的违规敏感词（比如：成绩飞跃，过目不忘，记住永不忘，通过率，高分王者，名列前茅，百分百高薪就业，国家承认，命题专家联手，圈定考试范围等）违反的次数和频率，依据触发条件规则提出警告或处理。为诸暨市市场监督局管理区域内规范企业为微信视频号直播行为，提供数据支持。将采集完成的直播视频进行进行预处理，第一步：基于原始视频文件，以最大10分钟单位对原始视频进行切片。第二步：对于已完成的切片视频，进行视频内容转语音操作。第三步：对于已完成视频转语音操作的切片，进行语音转文本操作。第四步：使用OCR技术对原始视频中抓取的图片进行文字提取操作。第五步：将所得到的文字内容与违法预警关键词库进行匹配。最终运用多标准决策分析模型，对主播在直播过程中出现的违规语句进行分析计算，得出违法预警值和是否预警判断。 违法预警值=（违法预警单关键词命中次数*0.25）+（违法预警组合关键词命中次数* 0.3）+（图片识别命中预警组合关键词个数*0.35）+（直播间近一个月历史违规记录数*0.1） 通过公式计算出最终违法预警值，违法预警值 ≤1 时，不触发预警提示，违法预警值 ＞1 时触发违法预警提示。
This dataset involves transcription and analysis of live stream content from education and training category influencers on the WeChat Video Channels platform. The spoken content of the streamers during live broadcasts is processed and analyzed. Based on the frequency and count of violations of pre-set sensitive prohibited keywords (such as "dramatic score improvement", "memorize instantly and forever", "remember permanently", "pass rate", "top scorer", "among the top ranks", "100% high-paying employment", "state-recognized", "jointly organized by exam experts", "designate exam scope", etc.) by the streamers during the live broadcast, warnings or corresponding treatments will be issued in accordance with the trigger rules. This dataset provides data support for the Market Supervision Administration of Zhuji City to regulate the live streaming behaviors of enterprises within its jurisdiction on WeChat Video Channels. The collected live stream videos undergo the following preprocessing steps: Step 1: Slice the original video files into segments with a maximum duration of 10 minutes each. Step 2: Convert the sliced video content into audio files. Step 3: Transcribe the audio from the sliced videos into text. Step 4: Extract text from images captured from the original videos using OCR technology. Step 5: Match the extracted text content against the illegal warning keyword database. Finally, a multi-criteria decision analysis (MCDA) model is used to analyze and calculate the violative statements made by the streamers during the live broadcast, to derive the Illegal Warning Score and make a warning determination. The formula for calculating the Illegal Warning Score is as follows: Illegal Warning Score = (Number of hits for single prohibited keywords * 0.25) + (Number of hits for combined prohibited keywords * 0.3) + (Number of combined warning keywords identified via image recognition * 0.35) + (Number of historical violation records of the live stream room in the past month * 0.1) After calculating the final Illegal Warning Score using the formula: no warning alert will be triggered when the score ≤ 1, and an illegal warning alert will be triggered when the score > 1.
