arXiv subjects

Kyoji Umemura

Publications and source records attributed to Kyoji Umemura.

At least 19 recordsLinked to original sources

arXiv2026

Mapping Social Media User Behaviors in Reciprocity Space

Social media users exhibit diverse behavioral patterns as platforms function simultaneously as information and friendship networks. We introduce a reciprocity-based framework mapping users onto two-dimensional space defined by bidirectional connection ratios. Analyzing 48,830 Twitter users and 149 million connections, we demonstrate that fragmented user types from prior studies (influencers, lurkers, brokers, and follow-back accounts) emerge naturally as regions within continuous behavioral space rather than discrete categories. User properties vary smoothly across the reciprocity dimensions, revealing clear behavioral gradients. This framework provides the first unified model encompassing the full spectrum of social media behaviors and offers interpretable metrics for influence measurement and platform design.

cs.SI↗

arXiv2023

Large Language Model-based System to Provide Immediate Feedback to Students in Flipped Classroom Preparation Learning

This paper proposes a system that uses large language models to provide immediate feedback to students in flipped classroom preparation learning. This study aimed to solve challenges in the flipped classroom model, such as ensuring that students are emotionally engaged and motivated to learn. Students often have questions about the content of lecture videos in the preparation of flipped classrooms, but it is difficult for teachers to answer them immediately. The proposed system was developed using the ChatGPT API on a video-watching support system for preparation learning that is being used in real practice. Answers from ChatGPT often do not align with the context of the student's question. Therefore, this paper also proposes a method to align the answer with the context. This paper also proposes a method to collect the teacher's answers to the students' questions and use them as additional guides for the students. This paper discusses the design and implementation of the proposed system.

cs.HC↗

arXiv2022

Comparing Two Counting Methods for Estimating the Probabilities of Strings

There are two methods for counting the number of occurrences of a string in another large string. One is to count the number of places where the string is found. The other is to determine how many pieces of string can be extracted without overlapping. The difference between the two becomes apparent when the string is part of a periodic pattern. This research reports that the difference is significant in estimating the occurrence probability of a pattern. In this study, the strings used in the experiments are approximated from time-series data. The task involves classifying strings by estimating the probability or computing the information quantity. First, the frequencies of all substrings of a string are computed. Each counting method may sometimes produce different frequencies for an identical string. Second, the probability of the most probable segmentation is selected. The probability of the string is the product of all probabilities of substrings in the selected segmentation. The classification results demonstrate that the difference in counting methods is statistically significant, and that the method without overlapping is better.

cs.DS↗

arXiv2022

Follower--Followee Ratio Category and User Vector for Analyzing Following Behavior

Analyzing following behavior is important in many applications. Following behavior may depend on the main intention of the follower. Users may either follow their friends or they may follow celebrities to know more about them. It is difficult to estimate users' intention from their following relationships. In this paper, we propose an approach to analyze following relationships. First, we investigated the similarity between users. Similar followers and followees are likely to be friends. However, when the follower and followee are not similar, it is likely that follower seeks to obtain more information on the followee. Second, we categorized users by the network structure. We then proposed analysis of following behavior based on similarity and category of users estimated from tweets and user data. We confirmed the feasibility of the proposed method through experiments. Finally, we examined users in different categories and analyzed their following behavior.

cs.SI↗

arXiv2021

Feature Selective Likelihood Ratio Estimator for Low- and Zero-frequency N-grams

In natural language processing (NLP), the likelihood ratios (LRs) of N-grams are often estimated from the frequency information. However, a corpus contains only a fraction of the possible N-grams, and most of them occur infrequently. Hence, we desire an LR estimator for low- and zero-frequency N-grams. One way to achieve this is to decompose the N-grams into discrete values, such as letters and words, and take the product of the LRs for the values. However, because this method deals with a large number of discrete values, the running time and memory usage for estimation are problematic. Moreover, use of unnecessary discrete values causes deterioration of the estimation accuracy. Therefore, this paper proposes combining the aforementioned method with the feature selection method used in document classification, and shows that our estimator provides effective and efficient estimation results for low- and zero-frequency N-grams.

cs.CL↗

arXiv2021

Comparison of Indicators of Location Homophily Using Twitter Follow Graph

Location homophily is a tendency of Twitter users whose followers tend to be in the same or nearby areas. Intuitively, although users with a higher number of follower relationships might have negative homophily indicators, it is worth consulting actual Twitter data. Moreover, there may be certain functions regarding the numbers of friends and followers that are more directly correlated to the homophily. In this study, the ratio of the number of friends to the number of followers is shown to be a more effective negative indicator of homophily, and the results for 10 different countries are verified.

cs.SI↗

arXiv2021

Unified Likelihood Ratio Estimation for High- to Zero-frequency N-grams

Likelihood ratios (LRs), which are commonly used for probabilistic data processing, are often estimated based on the frequency counts of individual elements obtained from samples. In natural language processing, an element can be a continuous sequence of $N$ items, called an $N$-gram, in which each item is a word, letter, etc. In this paper, we attempt to estimate LRs based on $N$-gram frequency information. A naive estimation approach that uses only $N$-gram frequencies is sensitive to low-frequency (rare) $N$-grams and not applicable to zero-frequency (unobserved) $N$-grams; these are known as the low- and zero-frequency problems, respectively. To address these problems, we propose a method for decomposing $N$-grams into item units and then applying their frequencies along with the original $N$-gram frequencies. Our method can obtain the estimates of unobserved $N$-grams by using the unit frequencies. Although using only unit frequencies ignores dependencies between items, our method takes advantage of the fact that certain items often co-occur in practice and therefore maintains their dependencies by using the relevant $N$-gram frequencies. We also introduce a regularization to achieve robust estimation for rare $N$-grams. Our experimental results demonstrate that our method is effective at solving both problems and can effectively control dependencies.

cs.CL↗

arXiv2020

Analysis of Short Dwell Time in Relation to User Interest in a News Application

Dwell time has been widely used in various fields to evaluate content quality and user engagement. Although many studies shown that content with long dwell time is good quality, contents with short dwell time have not been discussed in detail. We hypothesize that content with short dwell time is not always low quality and does not always have low user engagement, but is instead related to user interest. The purpose of this study is to clarify the meanings of short dwell time browsing in mobile news application. First, we analyze the relation of short dwell time to user interest using large scale user behavior logs from a mobile news application. This analysis was conducted on a vector space based on users click histories and then users and articles were mapped in the same space. The users with short dwell time are concentrated on a specific position in this space; thus, the length of dwell time is related to their interest. Moreover, we also analyze the characteristics of short dwell time browsing by excluding these browses from their click histories. Surprisingly, excluding short dwell time click history, it was found that short dwell time click history included some aspect of user interest in 30.87% of instances where the cluster of users changed. These findings demonstrate that short dwell time does not always indicate a low level of user engagement, but also level of user interest.

cs.IR↗

arXiv2020

The metrics of keywords to understand the difference between Retweet and Like in each category

The purpose of this study is to clarify what kind of news is easily retweeted and what kind of news is easily Liked. We believe these actions, retweeting and Liking, have different meanings for users. Understanding this difference is important for understanding people's interest in Twitter. To analyze the difference between retweets (RT) and Likes on Twitter in detail, we focus on word appearances in news titles. First, we calculate basic statistics and confirm that tweets containing news URLs have different RT and Like tendencies compared to other tweets. Next, we compared RTs and Likes for each category and confirmed that the tendency of categories is different. Therefore, we propose metrics for clarifying the differences in each action for each category used in the $χ$-square test in order to perform an analysis focusing on the topic. The proposed metrics are more useful than simple counts and TF-IDF for extracting meaningful words to understand the difference between RTs and Likes. We analyzed each category using the proposed metrics and quantitatively confirmed that the difference in the role of retweeting and Liking appeared in the content depending on the category. Moreover, by aggregating tweets chronologically, the results showed the trend of RT and Like as a list of words and clarified how the characteristic words of each week were related to current events for retweeting and Liking.

cs.IR↗

arXiv2019

User's Centrality Analysis for Home Location Estimation

User attributes, such as home location, are useful for many applications. Many researchers have been tackling how to estimate users' home locations using relationships among users. It is known that the home locations of certain users, such as celebrities, are hard to estimate using relationships. However, because estimating the home locations of all celebrities is not actually hard, it is important to clarify the characteristics of users whose home locations are hard to estimate. We analyze whether centralities, which represent users' characteristics, and the tendency to have the same home locations as friends are related. The results indicate that PageRank and HITS scores are related to whether users have the same home location as friends, and that users with higher HITS scores have the same home location as their friends less often. This result indicates that there are two types of users whose home locations are difficult to estimate: hub users who follow many celebrities and authority users who are celebrities.

cs.SI↗

arXiv2019

Usefulness of Instructor Annotations on Flipped Learning Preparation Video System

Flipped learning is a method that flips in/out class activities to make lectures learner-centered. In flipped learning, comments from learners on preparation material are useful information for instructors to consider before deciding in-class topics. Thus, we arrive at the notion that receiving comments from instructors will be effective for learners watching the video. By including annotations from instructors, we propose to improve the quality of content for learners and thus enhance learners' motivation and study satisfaction. To achieve this, we introduced "Steering Mark," a tool that enables learners to easily grasp the overall structure of a video, to the video learning system. We examined the effectiveness and influence of Steering Mark through an experiment with 34 undergraduate learners. As a result, Steering Mark was found to be useful in improving the quality of video content for learners.

cs.CY↗

arXiv2019

Journal Name Extraction from Japanese Scientific News Articles

In Japanese scientific news articles, although the research results are described clearly, the article's sources tend to be uncited. This makes it difficult for readers to know the details of the research. In this paper, we address the task of extracting journal names from Japanese scientific news articles. We hypothesize that a journal name is likely to occur in a specific context. To support the hypothesis, we construct a character-based method and extract journal names using this method. This method only uses the left and right context features of journal names. The results of the journal name extractions suggest that the distribution hypothesis plays an important role in identifying the journal names.

cs.CL↗

arXiv2019

Analysis of the Influence of Internet TV Station on Wikipedia Page Views

We aim to investigate the influence of television on the web; if the influence is strong, a viral effect may be expected. In this paper, we focus on the Internet TV station and on Wikipedia use as exploratory behavior on the web. We analyzed the influence of Internet TV station on Wikipedia page views. Our aim is to clarify the characteristics of page views as related to Internet TV station in order to index outward impact and develop a prediction model. The results indicate that there is a correlation between TV viewership and page views. Moreover we find that the time lag between TV and web gradually reduce as broadcasts begin after 9:00; after 23:00, page views tend to be maximized during the broadcast itself. We also differentiate between page views on PC and on mobile and find that PC pages tend to be accessed more during the daytime. In addition, we consider the number of broadcasts per program, and observe that viewership tends to stabilize as the number of broadcasts increases but that page views tend to decrease.

cs.CY↗

arXiv2019

Analysis of User Dwell Time on Non-News Pages

There is dwell time as one of the indicators of user's behavior, and this indicates how long a user looked at a page. Dwell time is especially useful in fields where user ratings are important, such as search engines, recommender systems, and advertisements are important. Despite the importance of this index, however, its characteristics are not well known. In this paper, we analyze the dwell times of various websites by desktop and mobile devices using data of one year. Our aim is to clarify the characteristics of dwell time on non-news websites in order to discover which features are effective for predicting the dwell time. In this analysis, we focus on device types, access times, behavior on the website, and scroll depth. The results indicated that the number of sessions decreased as the dwell time increased, for both desktop and mobile devices. We also found that hour and month greatly affected the dwell time, but day of the week had little effect. Moreover, we discovered that inside and click users tended to have longer dwell times than outside and non-click users. However, we can not find a relationship between dwell time and scroll depth. This is because even if a user browsed the bottom of the page, the user might not necessarily have read the entire page.

cs.HC↗

arXiv2018

Response Collector: A Video Learning System for Flipped Classrooms

The flipped classroom has become famous as an effective educational method that flips the purpose of classroom study and homework. In this paper, we propose a video learning system for flipped classrooms, called Response Collector, which enables students to record their responses to preparation videos. Our system provides response visualization for teachers and students to understand what they have acquired and questioned. We performed a practical user study of our system in a flipped classroom setup. The results show that students preferred to use the proposed method as the inputting method, rather than naive methods. Moreover, sharing responses among students was helpful for resolving individual students' questions, and students were satisfied with the use of our system.

cs.CY↗

arXiv2018

Computing Information Quantity as Similarity Measure for Music Classification Task

This paper proposes a novel method that can replace compression-based dissimilarity measure (CDM) in composer estimation task. The main features of the proposed method are clarity and scalability. First, since the proposed method is formalized by the information quantity, reproduction of the result is easier compared with the CDM method, where the result depends on a particular compression program. Second, the proposed method has a lower computational complexity in terms of the number of learning data compared with the CDM method. The number of correct results was compared with that of the CDM for the composer estimation task of five composers of 75 piano musical scores. The proposed method performed better than the CDM method that uses the file size compressed by a particular program.

cs.SD↗

arXiv2017

When Do Users Change Their Profile Information on Twitter?

We can see profile information such as name, description and location in order to know the user on social media. However, this profile information is not always fixed. If there is a change in the user's life, the profile information will be changed. In this study, we focus on user's profile information changes and analyze the timing and reasons for these changes on Twitter. The results indicate that the peak of profile information change occurs in April among Japanese users, but there was no such trend observed for English users throughout the year. Our analysis also shows that English users most frequently change their names on their birthdays, while Japanese users change their names as their Twitter engagement and activities decrease over time.

cs.SI↗

arXiv2017

Improving Compression Based Dissimilarity Measure for Music Score Analysis

In this paper, we propose a way to improve the compression based dissimilarity measure, CDM. We propose to use a modified value of the file size, where the original CDM uses an unmodified file size. Our application is a music score analysis. We have chosen piano pieces from five different composers. We have selected 75 famous pieces (15 pieces for each composer). We computed the distances among all pieces by using the modified CDM. We use the K-nearest neighbor method when we estimate the composer of each piece of music. The modified CDM shows improved accuracy. The difference is statistically significant.

cs.SD↗