农兽药类抖音直播带货违法监测预警数据

对采集的抖音平台带货品类为农兽药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：无毒，无害，100%安全，无残留，保证高产，立竿见影，无效退款，保险公司保险，2小时见效，权威机构专业认证，农业专家强烈推荐，无效包退等）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抖音直播行为，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 conducts transcription and analysis on the collected live streaming video content of agricultural and veterinary drug product influencers on the Douyin platform, and processes and analyzes the oral language content of the influencers. Warnings or penalties are issued based on the frequency and number of violations of pre-set sensitive prohibited keywords by influencers during live streaming, including but not limited to: non-toxic, harmless, 100% safe, no residue, guarantee high yield, immediate effect, money-back if ineffective, insured by insurance companies, takes effect within 2 hours, professionally certified by authoritative institutions, strongly recommended by agricultural experts, refund for invalid results, etc. This dataset provides data support for regulating the live streaming behaviors of enterprises on Douyin within the jurisdiction of the Zhuji Municipal Market Supervision Administration.

The collected live streaming videos undergo the following preprocessing steps:
1. Slice the original video files into chunks with a maximum duration of 10 minutes each;
2. Convert the sliced video content into speech audio;
3. Perform speech-to-text conversion on the sliced audio files that have completed video-to-speech conversion;
4. Extract text from images captured from the original videos using Optical Character Recognition (OCR) technology;
5. Match the obtained text content with the violation warning keyword database.

Finally, a multi-criteria decision analysis (MCDA) model is applied to analyze and calculate the prohibited statements uttered by the streamer during live streaming, to derive the violation early warning score and make a warning determination.
The formula for calculating the violation early warning score is as follows:
Violation Early Warning Score = (Number of hits for single prohibited keyword * 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)

The final violation early warning score is calculated using the above formula. No warning prompt will be triggered when the score ≤ 1, and a violation warning prompt will be triggered when the score > 1.

搜集汇总

数据集介绍

特点

该数据集用于监测抖音农兽药类直播带货中的违法行为，包含1552条记录，通过分析违规敏感词和组合关键词计算违法预警值，为市场监督提供数据支持。