Dark Mode
Post-Pandemic Philippine Smishing Data
Data Science and Analytics
Tags and Keywords
Trusted By
"No reviews yet"
Free
About
This collection contains logs of unsolicited marketing and fraudulent messages, commonly known as spam and scam SMS, personally received by the contributor within the Philippines. The data documents the proliferation of these digital threats, which saw a notable rise following the COVID-19 pandemic. It serves as a crucial resource for understanding local trends in mobile messaging abuse and the tactics employed by scammers in the region.
Columns
- masked_celphone_number: A partially obscured version of the mobile phone number associated with the message recipient.
- hashed_celphone_number: A unique identifier assigned to the mobile phone number using a hashing technique.
- date: The date and time (in UTC) when the message was received.
- text: The full content of the short message service (SMS) text.
- carrier: The specific mobile network operator (telecommunications company) responsible for carrying the message.
Distribution
The data is provided in a single CSV file, titled
SPAM_SMS.csv, which has a size of approximately 232.01 kB. It is structured with five distinct columns and contains 1014 valid records across all fields.Usage
This dataset is highly useful for telecommunications security analysis, research into phishing and smishing techniques, and regulatory efforts aimed at combating mobile fraud. It can be used to train machine learning models for SMS filtering, track shifts in scam language (linguistics), and assess the effectiveness of anti-spam measures implemented by network carriers and authorities.
Coverage
The data focuses exclusively on SMS activity within the Philippines (🇵🇭). The time span covered by the logged entries ranges from January 2018 up to August 2025 (based on minimum and maximum recorded dates). Note that the volume of new entries declined significantly starting in August 2024, attributed to joint anti-scam efforts by police and local telecommunications companies.
License
CC BY-NC-SA 4.0
Who Can Use It
- Data Scientists: For training spam detection algorithms and natural language processing (NLP) models.
- Mobile Network Providers: To identify high-risk phone prefixes, common scam patterns, and improve internal filtering mechanisms.
- Security Researchers: For studying regional cybercrime and fraud evolution post-pandemic.
- Academics: For sociolinguistic studies on persuasive language used in digital scams.
Dataset Name Suggestions
- Philippine Mobile Scam SMS Log
- Filipino Spam Text Repository
- SMS Fraud Log PH
- Post-Pandemic Philippine Smishing Data
Attributes
Original Data Source: Post-Pandemic Philippine Smishing Data
QUALITYLoading...