• Search Research Projects
  • Search Researchers
  • How to Use
  1. Back to project page

2019 Fiscal Year Final Research Report

A Study on Supporting Information Reliability Judgment by Presenting Global and Local Features of Web Pages

Research Project

  • PDF
Project/Area Number 17K00429
Research Category

Grant-in-Aid for Scientific Research (C)

Allocation TypeMulti-year Fund
Section一般
Research Field Web informatics, Service informatics
Research InstitutionUniversity of Hyogo

Principal Investigator

Yumoto Takayuki  兵庫県立大学, 工学研究科, 助教 (20453152)

Project Period (FY) 2017-04-01 – 2020-03-31
Keywords情報信頼性 / Webマイニング / 典型性 / 文体分類
Outline of Final Research Achievements

We proposed methods to estimate the typicality and writing style of sentences. They are used as criteria to judge the reliability of Web pages. The sentence typicality for a given keyword is estimated based on the co-occurrence relationship between words. In the writing style classification, four writing style classes are defined, distal style, direct style, conversational style, and slang style. We focus on sentence-final expression for the writing style classification, and we use sentence-final dictionaries automatically constructed from information source different for each style.

Free Research Field

情報検索

Academic Significance and Societal Importance of the Research Achievements

本研究では,文の典型性の推定手法と文体分類手法を開発した.文の典型性推定では,語の共起確率だけでなく,その予測値を併用することで推定精度を向上させた.文の典型性の推定結果をユーザに提示することにより,ユーザは典型性の低い文章については世間一般に認知されていない情報として警戒して閲覧することができるようになる.また,文体分類においては,定義した4つの文体に対して高い精度での分類を実現した.さらに,文体分類の応用として,文体による注目トピックの違いや文体と文章の難易度の関係についての分析を行った.

URL: 

Published: 2021-02-19  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi