4,992 social media posts from the RedNote platform categorized into 613 advertisement and 4,379 non-advertisement samples. The dataset includes 26,324 associated images distributed across training, validation, and test splits for covert marketing detection.
Use Cases
- Develop binary classification models to distinguish between 'Ad Posts' and 'Non-Ad Posts' using text and image features
- Train multimodal neural networks that process the 26,324 images alongside post metadata to identify hidden marketing intent
- Evaluate the performance of covert advertisement detection algorithms using the dedicated 1,000-sample test set
Strengths
- Contains 4,992 total posts split into 3,493 training, 499 validation, and 1,000 test samples
- Includes 26,324 images associated with social media posts to support multimodal analysis
- Features binary classification labels distinguishing between Ad Posts and Non-Ad Posts
- Focuses specifically on the RedNote (Xiaohongshu) platform, a major hub for social commerce and influencer marketing