|
|
Email spam filtering using artificial intelligence
Safonov, Yehor ; Uher, Václav (referee) ; Kolařík, Martin (advisor)
In the modern world, email communication defines itself as the most used technology for exchanging messages between users. It is based on three pillars which contribute to the popularity and stimulate its rapid growth. These pillars are represented by free availability, efficiency and intuitiveness during exchange of information. All of them constitute a significant advantage in the provision of communication services. On the other hand, the growing popularity of email technologies poses considerable security risks and transforms them into an universal tool for spreading unsolicited content. Potential attacks may be aimed at either a specific endpoints or whole computer infrastructures. Despite achieving high accuracy during spam filtering, traditional techniques do not often catch up to rapid growth and evolution of spam techniques. These approaches are affected by overfitting issues, converging into a poor local minimum, inefficiency in highdimensional data processing and have long-term maintainability issues. One of the main goals of this master's thesis is to develop and train deep neural networks using the latest machine learning techniques for successfully solving text-based spam classification problem belonging to the Natural Language Processing (NLP) domain. From a theoretical point of view, the master's thesis is focused on the e-mail communication area with an emphasis on spam filtering. Next parts of the thesis bring attention to the domain of machine learning and artificial neural networks, discuss principles of their operations and basic properties. The theoretical part also covers possible ways of applying described techniques to the area of text analysis and solving NLP. One of the key aspects of the study lies in a detailed comparison of current machine learning methods, their specifics and accuracy when applied to spam filtering. At the beginning of the practical part, focus will be placed on the e-mail dataset processing. This phase was divided into five stages with the motivation of maintaining key features of the raw data and increasing the final quality of the dataset. The created dataset was used for training, testing and validation of types of the chosen deep neural networks. Selected models ULMFiT, BERT and XLNet have been successfully implemented. The master's thesis includes a description of the final data adaptation, neural networks learning process, their testing and validation. In the end of the work, the implemented models are compared using a confusion matrix and possible improvements and concise conclusion are also outlined.
|
|
|
Email spam filtering using artificial intelligence
Safonov, Yehor ; Uher, Václav (referee) ; Kolařík, Martin (advisor)
In the modern world, email communication defines itself as the most used technology for exchanging messages between users. It is based on three pillars which contribute to the popularity and stimulate its rapid growth. These pillars are represented by free availability, efficiency and intuitiveness during exchange of information. All of them constitute a significant advantage in the provision of communication services. On the other hand, the growing popularity of email technologies poses considerable security risks and transforms them into an universal tool for spreading unsolicited content. Potential attacks may be aimed at either a specific endpoints or whole computer infrastructures. Despite achieving high accuracy during spam filtering, traditional techniques do not often catch up to rapid growth and evolution of spam techniques. These approaches are affected by overfitting issues, converging into a poor local minimum, inefficiency in highdimensional data processing and have long-term maintainability issues. One of the main goals of this master's thesis is to develop and train deep neural networks using the latest machine learning techniques for successfully solving text-based spam classification problem belonging to the Natural Language Processing (NLP) domain. From a theoretical point of view, the master's thesis is focused on the e-mail communication area with an emphasis on spam filtering. Next parts of the thesis bring attention to the domain of machine learning and artificial neural networks, discuss principles of their operations and basic properties. The theoretical part also covers possible ways of applying described techniques to the area of text analysis and solving NLP. One of the key aspects of the study lies in a detailed comparison of current machine learning methods, their specifics and accuracy when applied to spam filtering. At the beginning of the practical part, focus will be placed on the e-mail dataset processing. This phase was divided into five stages with the motivation of maintaining key features of the raw data and increasing the final quality of the dataset. The created dataset was used for training, testing and validation of types of the chosen deep neural networks. Selected models ULMFiT, BERT and XLNet have been successfully implemented. The master's thesis includes a description of the final data adaptation, neural networks learning process, their testing and validation. In the end of the work, the implemented models are compared using a confusion matrix and possible improvements and concise conclusion are also outlined.
|
|
|
Specific Features of Czech Deaf People's E-mail Communication in Official Communication Situations
Lavičková, Blanka ; Komorná, Marie (advisor) ; Macurová, Alena (referee)
This bachelor thesis deals with the stylistics of the written Czech used in e-mail correspondence by the Czech deaf. The main attention is focused on formal communication situations that take place on the intercultural level, i.e. between the non-deaf and deaf participants in communication. The aim of the thesis is to find out what stylistic means occur in situations with varying degrees of formality, and to what extent the deaf writers are familiarised with the stylistic standards of Czech - language that is foreign to them. The starting material comprises 185 e-mails from 67 deaf authors whose native or preferred communication language is Czech sign language. Keywords: Czech sign language, e-mail communication, deaf participant in communication, official communication situation, written Czech, stylistic means
|
|
|
Optimization of e-mail communication in the software company environment
Gubišová, Kristýna ; Bruckner, Tomáš (advisor) ; Nadrchal, Tomáš (referee)
C ommunication with the customer is very important pa rt of the marketing itself. Is very important to take care about acquired customer, because as soon as the company dissapointed him, it is very difficult to gain his trust and affection back. Thi s diploma thesis identifies e-mail marketing as a whole and deals with its current trends and examine how e-mail itself and his elements affect psyche and behavior of recipients and tries to iden tify ways to maintain consumer confidence. The thesis introduces e-mails from a practical envirome nt of the software company, in which are applied changes resulting from public opinion. These e-mail s are evaluated and compared with past versions of e-mails, these e-mails are evaluated and compare d with previous versions of e-mails.
|
|
|
E-mail marketing
TŮMOVÁ, Kateřina
The aim of this work is to specify the e-mail marketing and in the practical application to evaluate the pros and cons of e-mail marketing as a tool of targeted marketing communication.Based on personal interviews with representatives of the company was described their existing e-mail marketing.Through the survey it was found, how customers perceive the company's e-mail marketing.Based on the survey, changes were proposed at the end of the thesis.
|
guest ::
