arXiv subjects

Mitsuo Yoshida

Publications and source records attributed to Mitsuo Yoshida.

At least 37 records · Page 2Linked to original sources

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↗

arXiv2020

Brushing Feature Values in Immersive Graph Visualization Environment

There are a variety of graphs where multidimensional feature values are assigned to the nodes. Visualization of such datasets is not an easy task since they are complex and often huge. Immersive Analytics is a powerful approach to support the interactive exploration of such large and complex data. Many recent studies on graph visualization have applied immersive analytics frameworks. However, there have been few studies on immersive analytics for visualization of multidimensional attributes associated with the input graphs. This paper presents a new immersive analytics system that supports the interactive exploration of multidimensional feature values assigned to the nodes of input graphs. The presented system displays label-axes corresponding to the dimensions of feature values, and label-edges that connect label-axes and corresponding to the nodes. The system supports brushing operations which controls the display of edges that connect a label-axis and nodes of the graph. This paper introduces visualization examples with a graph dataset of Twitter users and reviews by experts on graph data analysis.

cs.HC↗

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

Analysis of Bias in Gathering Information Between User Attributes in News Application

In the process of information gathering on the web, confirmation bias is known to exist, exemplified in phenomena such as echo chambers and filter bubbles. Our purpose is to reveal how people consume news and discuss these phenomena. In web services, we are able to use action logs of a service to investigate these phenomena. However, many existing studies about these phenomena are conducted via questionnaires, and there are few studies using action logs. In this paper, we attempt to discover biases of information gathering due to differences in user demographic attributes, such as age and gender, from the behavior log of the news distribution service. First, we summarized the actions in the service for each user attribute and showed the difference of user behavior depending on the attributes. Next, the degree of correlation between the attributes was measured using the correlation coefficient, and a strong correlation was found to exist in the browsing tendency of the news articles between the attributes. Then, the bias of keywords between attributes was discovered, keywords with bias in behavior among the attributes were found using parameters of regression analysis. Since these discovered keywords are almost explainable by big news, our proposed method is effective in detecting biased keywords.

cs.CY↗

arXiv2019

Analysis of User Dwell Time by Category in News Application

Dwell time indicates how long a user looked at a page, and this is used especially in fields where ratings from users 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 time of news pages according to category in smartphone application. Our aim is to clarify the characteristics of dwell time and the relation between length of news page and dwell time, for each category. The results indicated different dwell time trends for each category. For example, the social category had fewer news pages with shorter dwell time than peaks, compared to other categories, and there were a few news pages with remarkably short dwell time. We also found a large difference by category in the correlation value between dwell time and length of news page. Specifically, political news had the highest correlation value and technology news had the lowest. In addition, we found that a user tends to get sufficient information about the news content from the news title in short dwell times.

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

Analysis of Political Party Twitter Accounts' Retweeters During Japan's 2017 Election

In modern election campaigns, political parties utilize social media to advertise their policies and candidates and to communicate to the electorate. In Japan's latest general election in 2017, the 48th general election for the Lower House, social media, especially Twitter, was actively used. In this paper, we analyze the users who retweeted tweets of political parties on Twitter during the election. Our aim is to clarify what kinds of users are diffusing (retweeting) tweets of political parties. The results indicate that the characteristics of retweeters of the largest ruling party (Liberal Democratic Party of Japan) and the largest opposition party (The Constitutional Democratic Party of Japan) were similar, even though the retweeters did not overlap each other. We also found that a particular opposition party (Japanese Communist Party) had quite different characteristics from other political parties.

cs.SI↗

arXiv2018

Information Diffusion Power of Political Party Twitter Accounts During Japan's 2017 Election

In modern election campaigns, political parties utilize social media to advertise their policies and candidates and to communicate to electorates. In Japan's latest general election in 2017, the 48th general election for the Lower House, social media, especially Twitter, was actively used. In this paper, we perform a detailed analysis of social graphs and users who retweeted tweets of political parties during the election. Our aim is to obtain accurate information regarding the diffusion power for each party rather than just the number of followers. The results indicate that a user following a user who follows a political party account tended to also follow the account. This means that it does not increase diversity because users who follow each other tend to share similar values. We also find that followers of a specific party frequently retweeted the tweets. However, since users following the user who follow a political party account are not diverse, political parties delivered the information only to a few political detachment users.

cs.SI↗

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

Do Political Detachment Users Receive Various Political Information on Social Media?

In the election, political parties communicate political information to people through social media. The followers receive the information, but can users who are not followers, political detachment users, receive the information? We focus on political detachment users who do not follow any political parties, and tackle the following research question: do political detachment users receive various political information during the election period? The results indicate that the answer is No. We determined that the political detachment users only receive the information of a few political parties.

cs.SI↗

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↗

arXiv2017

Polysemy Detection in Distributed Representation of Word Sense

In this paper, we propose a statistical test to determine whether a given word is used as a polysemic word or not. The statistic of the word in this test roughly corresponds to the fluctuation in the senses of the neighboring words a nd the word itself. Even though the sense of a word corresponds to a single vector, we discuss how polysemy of the words affects the position of vectors. Finally, we also explain the method to detect this effect.

cs.DS↗