Bi-Term Topic Model for SMS Classification

2017 ◽  
Vol 13 (2) ◽  
pp. 28-40
Author(s):  
Jialin Ma ◽  
Yongjun Zhang ◽  
Lin Zhang ◽  
Kun Yu ◽  
Jinlin Liu
Keyword(s):  
Text Classification ◽  
Short Message Service ◽  
Topic Model ◽  
Classification Algorithms ◽  
Short Message ◽  
Semantic Features ◽  
Spam Filtering ◽  
Proposed Model ◽  
Message Service

With the overflowing of Short Message Service (SMS) spam nowadays, many traditional text classification algorithms are used for SMS spam filtering. Nevertheless, because the content of SMS spam messages are miscellaneous and distinct from general text files, such as more shorter, usually including mass of abbreviations, symbols, variant words and distort or deform sentences, the traditional classifiers aren't fit for the task of SMS spam filtering. In this paper, the authors propose a Short Message Biterm Topic Model (SM-BTM) which can be used to automatically learn latent semantic features from SMS spam corpus for the task of SMS spam filtering. The SM-BTM is based on the probability of topic model theory and Biterm Topic Model (BTM). The experiments in this work show the proposed model SM-BTM can acquire higher quality of topic features than the original BTM, and is more suitable for identifying the miscellaneous SMS spam.

A Message Topic Model for Multi-Grain SMS Spam Filtering

2016 ◽  
Vol 12 (2) ◽  
pp. 83-95 ◽  
Author(s):  
Jialin Ma ◽  
Yongjun Zhang ◽  
Zhijian Wang ◽  
Kun Yu
Keyword(s):  
Text Classification ◽  
Short Message Service ◽  
Topic Model ◽  
Short Message ◽  
Spam Filtering ◽  
The Public ◽  
Data Problem ◽  
Message Service ◽  
Noise Data ◽  
Sparse Data Problem

At present, content-based methods are regard as the more effective in the task of Short Message Service (SMS) spam filtering. However, they usually use traditional text classification technologies, which are more suitable to deal with normal long texts; therefore, it often faces some serious challenges, such as the sparse data problem and noise data in the SMS message. In addition, the existing SMS spam filtering methods usually consider the SMS spam task as a binary-class problem, which could not provide for different categories for multi-grain SMS spam filtering. In this paper, the authors propose a message topic model (MTM) for multi-grain SMS spam filtering. The MTM derives from the famous probability topic model, and is improved in this paper to make it more suitable for SMS spam filtering. Finally, the authors compare the MTM with the SVM and the standard LDA on the public SMS spam corpus. The experimental results show that the MTM is more effective for the task of SMS spam filtering.

scholarly journals GSM based dual power enhanced LED display notice board with motion detector

2018 ◽  
Vol 7 (2.8) ◽  
pp. 559
Author(s):  
Gowrishankar Kasilingam ◽  
K Nithiyananthan ◽  
Priyanka Ramesh Mani ◽  
Sunil Thomas
Keyword(s):  
Short Message Service ◽  
Light Emitting Diode ◽  
Short Message ◽  
Motion Detector ◽  
Light Emitting ◽  
Ac Power ◽  
Proposed Model ◽  
Message Service ◽  
Notice Board

In this paper, a new improved Light Emitting Diode (LED) Display notice board with GSM technology has been created to plugs in all the drawbacks in existing framework. The proposed model has an excellent display notice board to display notices or messages at places that require real-time visibility, thereby transferring messages by Short Message Service (SMS) through cellular device. The proposed work in this paper elaborately narrates the procedure to construct a display notice board that has the quality of displaying messages in continuously running mode, and enabling the user to alter the ongoing message using SMS instantaneously. This system also has the feasibility to bind with other devices such as PC or laptop. The best feature of proposed system is the dual system for changing messages. And also utilizes two way power supply such as Renewable energy (Solar Power) and AC power. This feature enables the proposed model to work under any situations which overcomes the drawback in the existing display notice boards. Additionally, a motion detector has been included which turn ON or OFF the system automatically if any motion is not sensed.

A quantitative analysis of the Quality of Service of Short Message Service in the Philippines

2010 ◽  
Author(s):  
Marnelli Canlas ◽  
Kristoffer Paolo Cruz ◽  
Ma. Kristle Dimarucut ◽  
Patrick Uyengco ◽  
Gregory Tangonan ◽  
...  
Keyword(s):  
Quality Of Service ◽  
Quantitative Analysis ◽  
Short Message Service ◽  
The Philippines ◽  
Short Message ◽  
Message Service

Smishing Detection: Using Artificial Intelligence

2021 ◽  
Vol 9 (8) ◽  
pp. 2218-2224
Author(s):  
Samyak Sadanand Shravasti
Keyword(s):  
Artificial Intelligence ◽  
Short Message Service ◽  
Personal Information ◽  
Critical Issue ◽  
Cyber Attacks ◽  
Sensitive Information ◽  
Short Message ◽  
Proposed Model ◽  
Message Service ◽  
A Company

Abstract: Phishing occurs when people's personal information is stolen via email, phone, or text communications. In Smishing Short Message Service (SMS) is used for cyber-attacks, Smishing is a type of theft of sensitive information. People are more likely to give personal information such as account details and passwords when they receive SMS messages. This data could be used to steal money or personal information from a person or a company. As a result, Smishing is a critical issue to consider. The proposed model uses an Artificial Intelligence to detect smishing. Analysing a SMS and successfully detecting Smishing is possible. Finally, we evaluate and analyse our proposed model to show its efficacy. Keywords: Phishing, Smishing, Artificial Intelligence, LSTM, RNN

VP209 Two-Way Short Message Service (SMS) For Better Engagement And Quality Bio-Surveillance System

2017 ◽  
Vol 33 (S1) ◽  
pp. 247-248 ◽  
Author(s):  
Linh Dang ◽  
Jordan Wong ◽  
Thuy Le ◽  
Ngoc Phan ◽  
Spencer James ◽  
...  
Keyword(s):  
Short Message Service ◽  
Reporting System ◽  
Scale Up ◽  
Data Repository ◽  
Health Staff ◽  
Short Message ◽  
Quality Of Reporting ◽  
Practical Utilization ◽  
Message Service

INTRODUCTION:Along with the exponential growth of technology, the use of mobile devices in health, or mHealth, has been quickly becoming a viable practice to strengthen health systems, especially in low-resource settings. Nevertheless, the majority of mHealth interventions are pilot efforts which mostly lack robust design and evidence about the use of mHealth in public health. This study assessed the use of a bi-directional Short Message Service (SMS) in disease surveillance in Vietnam and aimed to bring evidence in improving engagement of health staff as well as the quality of reporting.METHODS:Eighty health staff from fourty communes of Hoa Binh and Hung Yen provinces were trained and participated in two 6-month pilots: one with one-way, and one with a bi-directional SMS system for assisting in error screening, and reminder and feedback provision to report two diseases: influenza and diarrhea using cell phones. After each examination and checking-in onto the paper logbook, participants reported the case by texting an SMS to a designated number and made notes of successfully reported cases. A central data repository server was set up to collect SMS reports, and aggregate reported patient data. Engagement of health staff and quality of the reporting work were assessed by the evaluation of the qualitative questionnaires, and the comparison of the texted SMS reports to the patient logbooks.RESULTS:With the use of a two-way versus one-way SMS system, participants were 4.6 times more likely (95 percent Confidence Interval, CI 3.93-5.44, p< .001) to send correctly formatted text reports, and 3.4 times more likely (95 percent CI 2.72-4.33, p< .001) to have precise information in their texted messages. Results also revealed that while their position, age, or gender of participants did not statistically influence the results, ethnicity and management roles did.CONCLUSIONS:The study showed that the use of a bi-directional SMS-based reporting system both significantly improved participants engagement in the reporting protocol, and greatly enhanced their reporting quality. The study demonstrated that robust evidence of a practical utilization of SMS in a disease reporting system to replace the traditional paper-based one has great potential for a scale-up and national-wide implementation.

scholarly journals TELEGRAM MESSENGER BOT FOR REALTIME MINE OPERATION REPORTS

2020 ◽  
Vol 1 (1) ◽  
pp. 253-262
Author(s):  
Reza Ardhianto
Keyword(s):  
Management System ◽  
Short Message Service ◽  
Fleet Management ◽  
Short Message ◽  
Quality Of Information ◽  
Data Analyst ◽  
Message Service ◽  
Operational Activities ◽  
The Cost

ABSTRAKInformasi realtime sangat penting untuk mendukung kegiatan operasional di tambang Batu Hijau PT. Amman Mineral Nusa tenggara. Selama ini salah satu metode yang digunakan dalam pendistribusian informasi realtime adalah dengan menggunakan MORS SMS Broadcaster yang telah dikembangkan oleh seksi Fleet Management System & Data Analyst yang memanfaatkan layanan GSM Short Message Service (SMS) dari operator seluler. Namun seiring dengan bertambahnya informasi yang harus diberikan dan semakin banyak jumlah pengguna layanan tersebut menjadikan pendistribusian informasi menggunakan SMS semakin tidak efektif dari sisi biaya. Keterbatasan dari sisi format pesan jumlah karakter yang dapat dikirimkan menggunakan layanan SMS juga semakin menurunkan kualitas informasi yang dapat diberikan. Untuk mengatasi kekurangan yang ada di sistem sebelumnya, perlu dikembangkan sistem/layanan baru dalam pendistribusian informasi realtime yang lebih efisien dari sisi biaya dan dapat meningkatkan kualitasi informasi yang disampaikan. Dari perbandingan terhadap beberapa alternatif aplikasi yang sejenis, Telegram dipilih untuk digunakan dalam pengembangan sistem baru karena lebih unggul dalam beberapa parameter perbandingan yang telah ditetapkan. Penggunaan fitur Telegram Bot juga telah memberikan dampak signifikan terhadap efisiensi biaya dan kualitas informasi laporan yang diberikan untuk mendukung kegiatan operasional dalam menjaga dan meningkatkan produktivitas tambang. Kata Kunci : informasi realtime, Short Message Service, Telegram, Bot, produktivitas tambang   ABSTRACT Realtime information is very important to support operational activities at PT. Amman Mineral Nusa Tenggara’s Batu Hijau mine. One of the methods used in the distribution of realtime information is to use MORS SMS Broadcaster which has been developed by the Fleet Management System & Data Analyst section that utilizes GSM Short Message Service (SMS) services from cellular operators. But along with the increase in information that need to be provided and the increasing number of users of these service makes the distribution of information using SMS increasingly ineffective in terms of cost. Limitations in message format and the number of characters that can be sent in a single SMS also further degrades the quality of information that can be provided. To overcome the weaknesses that exist in the previous system, new systems / services need to be developed to distribute realtime information that is more efficient in terms of cost and can improve the quality of information delivered. From a comparison of several similar application alternatives, Telegram was chosen for use in the development of a new system because it was superior in a number of predetermined comparison parameters. The use of the Telegram Bot feature has also had a significant impact on the cost efficiency and quality of report information delivery to support operational activities in maintaining and increasing mine productivity.  Keywords : realtime information, Short Message Service, Telegram, Bot, mine productivity 

Sign in / Sign up

Export Citation Format

Share Document