游戏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游戏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：玩到停不下来、不限时、一夜暴富、学生、真金白银、免费兑换、18禁、充的越多越厉害、百万收入不是梦、畅玩等）违反的次数和频率，依据触发条件规则提出警告或处理。为服务辖区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 ≤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 performs transcription and analysis on collected live stream videos of game-category influencers on the Douyin platform, processing and analyzing the spoken content of the influencers. Based on the number and frequency of violations of pre-configured sensitive violation keywords (including but not limited to "can't stop playing", "unlimited time", "get rich overnight", "students", "real money", "free redemption", "18+ restricted", "the more you recharge, the stronger you become", "a million-dollar income is no dream", "unrestricted play") during live broadcasts, warnings or penalties will be issued in accordance with the triggering condition rules. This work provides data support for the local Market Supervision Bureau to standardize the live streaming behaviors of enterprises within its jurisdiction on Douyin.
The collected live stream videos undergo the following preprocessing procedures:
1. Slice the original video files into chunks with a maximum duration of 10 minutes per chunk.
2. Extract speech content from each sliced video.
3. Convert the extracted speech content into text using speech-to-text technology.
4. Extract text from images captured from the original videos via Optical Character Recognition (OCR) technology.
5. Match the obtained text content against the pre-built violation warning keyword database.
Finally, a multi-criteria decision analysis (MCDA) model is utilized to analyze and calculate the violating statements made by the streamer during the live broadcast, generating a violation warning score and a warning judgment. If the violation warning score is ≤ 1, no warning alert will be triggered; if the score is > 1, a violation warning alert will be activated.

搜集汇总

数据集介绍

特点

该数据集主要用于监测抖音平台游戏类直播中的违法行为，通过分析直播内容中的违规敏感词来提供预警。数据集包含1134条记录，每季度更新，适用于市场监督局规范企业直播行为。数据处理流程包括视频切片、语音转文本和关键词匹配等步骤。