Seongmin Mun

Seongmin Mun
University Paris Nanterre · Science du langage

Ph.D Candidate

About

29
Publications
7,349
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
41
Citations
Introduction
Seongmin is a Ph.D. candidate in University Paris Ouest Nanterre. His research interests include language recognition system, computational linguistics, data visualization, and machine learning. Seongmin is currently working as a graduate student researcher and also a freelance data analysis lecturer. Reach out to simon.seongmin.mun@gmail.com to connect! See more details with his personal homepage (https://seongmin-mun.github.io/MyWebsite/Seongmin/index.html).
Additional affiliations
February 2016 - present
University Paris Nanterre
Position
  • PhD Student
March 2014 - February 2016
Ajou University
Position
  • PhD Student

Publications

Publications (29)
Article
Full-text available
This paper suggests a method for refining a massive amount of collective intelligence data and visualizing it with a multilevel sentiment network in order to understand the relevant information in an intuitive and semantic way. This semantic interpretation method minimizes network learning in the system as a fixed network topology only exists as a...
Article
Full-text available
Background: History studies involve the discovery of new facts based upon the records as well as understanding relationships between historic events and figures. However, a vast amount of resources, background knowledge and time would be required for empirical historical research. Visual analysis has the advantage of allowing users to easily identi...
Conference Paper
Full-text available
Temporal event data such as diagnosis records of multiple demen- tia patients include both multivariate data features and temporal changes. Analyzing temporal event data can reveal changing pat- terns by time or by correlations between target data and others. It is challenging but to explore visually both of multivariate data features and temporal...
Presentation
Full-text available
Multiword expressions (MWEs) are strings of two or more lexemes that are idiosyncratic in some respect. Such complex strings are frequent. Sag et al. (2002) estimate that 41% of the entries in WordNet 1.7 are MWEs. MWEs assume a wide range of forms such as institutionalized phrases and clichés (love conquers all), idioms (kick the bucket), fixed ph...
Presentation
Full-text available
Rhapsodie is a 33000-word treebank of spoken French that is annotated for syntax and prosody. It breaks down into 57 five-minute long samples produced by 89 male and female speakers. The discourse profile of each sample is captured by six variables: event structure (dialogue vs. monologue), social context (public vs. private), genre (argumentation,...
Conference Paper
Full-text available
Words in the corpus include features and information, and the visualizing of such words can improve the user’s understanding of them. Words in text corpus may be consist of one-word or they may be a combination of words that together, constitute a word. The latter is referred to as a multiword expression. And if we analyze both single word and mult...
Article
Full-text available
Background The editorial history of Wikipedia articles, especially those on controversial topics, shows the evolution of the topic and cues on whether they were written impartially. This study suggested a compact information-rich visual representation for a better understanding of the complex public discourse in a more intuitive and effective way....
Poster
Full-text available
Topics in a text corpus include features and information. Analyzing these topics can improve a user’s understanding of the corpus. These topics can be divided into two types: those whose meaning can be described in one word and those whose meaning in expressed through a recurring combination of words, also known as multiword expressions (MWE). Out...
Conference Paper
Full-text available
History studies involve discovering new facts based upon the records as well as understanding relationships between historic events and figures. However, a vast amount of resources, background knowledge and time would be required for empirical historical research. The Genealogy of the Kwon family and Annals of the Joseon Dynasty, both of which are...
Conference Paper
Full-text available
A decision tree is one of the predictive models in data mining and has been widely used in recent medical-data analyses [1]. In the finding of an important node, the existing decision-tree visualizations are used to show the ratio of the sample number to the target variable. Additional decisionvariable information, however, is needed since the deci...
Conference Paper
Full-text available
Topics in a text corpus include features and information; visualizing these topics can improve a user’s understanding of the corpus. Topics can be broadly divided into two categories: those whose meaning can be described in one word and those whose meaning in expressed through a combination of words. The latter type can be described as multiword ex...
Article
Full-text available
This research aims to analyze Twitter marketing strategies by focusing on tweets posted by four corporate Twitter accounts. We classified the posts by the four accounts into six types: daily life, general public relation(PR), event, professional information, customer service and retweet. And compared through Anova and Cluster analysis. In-depth ana...
Article
Full-text available
Predictive analysis is based on a probabilistic learning algorithm called pattern recognition or machine learning. Therefore, if users want to extract more information from the data, they are required high statistical knowledge. In addition, it is difficult to find out data pattern and characteristics of the data. This study conducted statistical d...
Conference Paper
Full-text available
The rapid development of the Web 2.0 era has generated a huge amount of online word-of-mouth information, which has influenced the society in various fields. Effects of Word of Mouth on movies, in particular, has become the new standards to evaluate a movie that affects potential audiences’ decision. Therefore, this research proposes a methodology...
Article
Full-text available
This paper suggests a method to refine a massive collective intelligence data, and visualize with multilevel sentiment network, in order to understand information in an intuitive and semantic way. For this study, we first calculated a frequency of sentiment words from each movie review. Second, we designed a Heatmap visualization to effectively dis...
Article
Full-text available
Recently, researches for the word of mouth(WOM) imply that consumers use WOM informations of products in their purchase process. This study suggests methods using opinion mining and visualization to understand consumers’ opinion of each goods and each markets. For this study we conduct research that includes developing domain ontology based on revi...
Poster
Full-text available
The research is conducting about the e ect of online information to society by producing online information from internet user after the web 2.0age. However, there is limitation that it costs a lot to analyze online information by human and to solve this, opinion minding is used which is automation system to analyze online information. This researc...
Conference Paper
Full-text available
In this paper, we present interactive visualization methods that analyze the relations between nations from UN General Assembly (UNGA) voting data. Our methods visualize the relations in several aspects such as specific issues or time period. UNGA voting data contains of 5211 resolutions from 1946 to 2012. For this work, we designed a similarity, m...
Article
Full-text available
This study aims to understand distribution of the sentimental words on each genre and find relationship between box office performance and sentimental words in movie review using 673 movies that have more than 1,000 reviews. For the analysis, crawling movie reviews and made data was composed movie genre, movie name, sales, attendance, screen, norma...
Article
Full-text available
In this study, we proposed Interactive Visualization methods that can be analyzed relations between nations in various viewpoints such as period, issue using total 5211 of the UN General Assembly voting data.For this research, we devised a similarity matrix between nations and developed two visualization method based similarity matrix. The first on...
Conference Paper
Full-text available
This research aims to analyze Twitter marketing strategies by focusing on tweets posted by four corporate Twitter accounts. We classified the posts by the four accounts into six types: daily life, general public relation (PR), event, professional information, customer service and retweet. We aimed to identify key players using an influence formula...
Article
Full-text available
In considering the overheated competition amongst social commerce, it is imperative to determine which parts of the social commerce service are considered important by consumers, and which parts need improvements to sustain relationship between consumers and the corporation. Therefore, this research has identified the motives for usages of consumer...

Network

Cited By