Digital Library[ Search Result ]
Proposal of a Graph Based Chat Message Analysis Model for Messenger User Verification
http://doi.org/10.5626/JOK.2022.49.9.696
As crimes and accidents through messengers increase, the necessity of verifying messenger users is emerging. In this study, two graph-based messenger user verification models that apply the traditional author verification problem to chat text were proposed. First, the graph random walk model builds an n-gram transition graph with a previous chat message and verifies the user by learning the characteristic of traversing the transition graph with a message whose author is unknown. The results showed an accuracy of 86% in 10,000 chat conversations. Second, the graph volume model verified the user using the characteristic that the size of the transition graph increased over time and achieved an accuracy of 87% in 1,000 chat conversations. When the density of the chat messages was calculated based on the transmission time, both graph models could guarantee more than 80% accuracy when the chat density was 15 or more.
A Cross-Texting Prevention System Using Syntactic Characteristics of Chat Messages
http://doi.org/10.5626/JOK.2021.48.6.639
Cross-texting refers to accidentally sending a message to an unintended person. It occurs frequently when users chat with multiple counterparts at the same time. Messengers mainly provide a function of canceling sending, but it is only post solution, and users find it difficult to prevent mistakes in advance. In this paper, we proposed a cross-texting detection model by analyzing the syntactic characteristics of chat sentences. It modelizes the previous chat messages of a specific user by extracting the honorifics and completeness features from chat messages, and detects the cross-texting cases by determining whether the target sentences are in accordance with the user chat message model. This approach is significant as it solves the cross-texting detection problem only with syntactic characteristics without semantic analysis by modeling the consistency of the user"s chat attitude. The proposed model detect cross-texting cases with an accuracy of 85.5% from automatically generated data using a real messenger dialogue corpus.
Search
Journal of KIISE
- ISSN : 2383-630X(Print)
- ISSN : 2383-6296(Electronic)
- KCI Accredited Journal
Editorial Office
- Tel. +82-2-588-9240
- Fax. +82-2-521-1352
- E-mail. chwoo@kiise.or.kr