研究方法 · Skill · 站内全文
评论研究方法
原作者研究方法，English。文内工具与接口按原文保留；本页供研读，实际使用的依赖见参考文件。
本资料包的参考文件（5）
本页目录
Comments Analysis
Mine a single post's comment section for sentiment and themes.
Setup gate
[ -z "${TIKHUB_API_KEY:-}" ] && echo "Set TIKHUB_API_KEY first (see tikhub-onboarding)."
Workflow
- Identify the post (platform + id/URL).
- Fetch comments, paginating to a target count (cap it):
- TikTok:
app/v3/fetch_video_comments(aweme_id,cursor). Douyin:app/v3/fetch_video_comments(aweme_id,cursor). - Instagram:
v2/fetch_post_comments(+fetch_comment_replies). - YouTube:
web_v2/get_video_comments(+get_video_comment_replies). - Twitter:
web/fetch_post_comments. Xiaohongshu:app_v2/get_note_comments.
- TikTok:
- Optional fast keywords: TikTok
analytics/fetch_comment_keywords(item_id) gives a comment keyword summary directly. - Analyze: sentiment breakdown, top themes with example quotes, most-liked comments, and any recurring questions/complaints.
- Deliver a summary with cited example comments.
Cost awareness
Each comment page (and reply page) is a billed call. Cap pages; warn for viral posts with huge
threads. Estimate via calculate_price.
Verification gate
- Comments fetched and tied to the right post.
- Themes/sentiment backed by quoted comments.
- Report the sample size (comments analyzed vs. total).
Red flags
- Summarizing 50 comments on a 50k-comment post as representative — disclose the sample.
- Unbounded reply pagination.
