From 993cf457144ff70958a401e6897b06955cebb805 Mon Sep 17 00:00:00 2001 From: Jieyab89 Date: Thu, 13 Aug 2026 01:35:17 +0700 Subject: [PATCH] add dict sentiment from local dataset && update reouces --- README.md | 4 +++- Script/SOCMINT-Twitter/sentiment.py | 3 ++- 2 files changed, 5 insertions(+), 2 deletions(-) diff --git a/README.md b/README.md index 365d8e9..7f5f686 100644 --- a/README.md +++ b/README.md @@ -1976,10 +1976,12 @@ For this case u must know the context also dorking for better results - [patreon](https://www.patreon.com/) You must to dork - [weibo](https://weibo.com/) You must to dork - [linktr](https://linktr.ee/) You must to dork +- [jakartapartyclub](https://jakartapartyclub.com/) +- [jakarta100bars](https://www.jakarta100bars.com/) Pro Tips -Note is for investigator like search scandal, deepfake porn or blackmail, red district review, women, dating platform and porn actress. Searching for scandal or blackmail or deepfake porn doesn't have to be on the listed sites, there are many perpetrators uploading on several platforms You need to do massive scrapping to collect this information, but there are times when they do it on platforms such as telegram, X or adult sites, you can search using dork, regex and linguistic like slang, abbreviation of word and other things +Note is for investigator like search scandal, deepfake porn or blackmail, red district review, night life and club, women, dating platform and porn actress. Searching for scandal or blackmail or deepfake porn doesn't have to be on the listed sites, there are many perpetrators uploading on several platforms You need to do massive scrapping to collect this information, but there are times when they do it on platforms such as telegram, X or adult sites, you can search using dork, regex and linguistic like slang, abbreviation of word and other things # Steam diff --git a/Script/SOCMINT-Twitter/sentiment.py b/Script/SOCMINT-Twitter/sentiment.py index 755907a..e1ea32d 100644 --- a/Script/SOCMINT-Twitter/sentiment.py +++ b/Script/SOCMINT-Twitter/sentiment.py @@ -148,7 +148,8 @@ NEGATIVE_WORDS = { "zionist", "bodo", "ludahi", "ludahin", "penjajah", "pajet", "pajeet", "cemoohan", "cemooh", "rusuh", "barbar", "paj3t", "cuih", "ngibul", "boong", "pekok", "pea", "pantek", "pantat", - "Anak haram", "asbun", + "Anak haram", "asbun", "omon-omon", "omon2", "ndasmu", "Endasmu", + "Nyenyenye", } # Flips the polarity of a sentiment word found within NEGATION_WINDOW tokens