English  |  正體中文  |  简体中文  |  全文筆數/總筆數 : 80990/80990 (100%)
造訪人次 : 41625283      線上人數 : 1927
RC Version 7.0 © Powered By DSPACE, MIT. Enhanced by NTU Library IR team.
搜尋範圍 查詢小技巧:
  • 您可在西文檢索詞彙前後加上"雙引號",以獲取較精準的檢索結果
  • 若欲以作者姓名搜尋,建議至進階搜尋限定作者欄位,可獲得較完整資料
  • 進階搜尋


    請使用永久網址來引用或連結此文件: http://ir.lib.ncu.edu.tw/handle/987654321/85861


    題名: 以社群網站照片顏色預測人格特質之研究;Study of predicting personality traits through social media image color
    作者: 陳俞君;CHEN, YU-CHUN
    貢獻者: 企業管理學系
    關鍵詞: 社群網站照片;顏色心理學;人格特質;主色調;支持向量機;隨機森林;social media images;color psychology;personality traits;dominant color;SVM;Random forest
    日期: 2021-07-13
    上傳時間: 2021-12-07 11:35:06 (UTC+8)
    出版者: 國立中央大學
    摘要: 人格特質是人類行為中心部分,由情感、行為、思維模式、情感組成,使人成為獨一無二的人。依照extended real-life hypothesis提到社群網站可能構成一個擴展的社會環境,因為社群網站集成了各種個人訊息,這些訊息都與人格特質相關。透過人格特質來了解不同群體,以便提高廣告、促銷、推薦以及其他行銷目的的有效性甚至是個人化,也有助於企業招募人才、衡量工作績效,或是其他用途。
    在顏色心理學中顏色偏好被認為是影響人潛在人格的關鍵,過去從社群網站上的使用者照片顏色判斷人格特質的研究中,尚未有以顏色心理學提出的顏色應用在社群網站的照片與人格特質做連結,因此本研究想探討透過顏色心理學的角度是否能更好的了解人格特質;加上,過去研究將照片顏色是以色相取平均值作為輸入,遭到其他研究駁斥,因此本研究假設透過一張照片中單個顏色成分最多的部分作為的主色相(dominant color)可以更好的區分圖像中的主要區域。
    本研究蒐集受測者社群網站上1080張照片,萃取照片主色調以顏色心理學連結,再以支持向量機(SVM)、隨機森林(Random forest)訓練預測模型並預測受測者之人格特質。
    實驗結果首先證實了顏色心理學所述顏色偏好影響人格特質;其次是以照片主色調更可以預測人格特質,使用隨機森林最好的預測準確率高達0.95;最重要的發現是使用資料集一,可使預測準確率大幅提升。
    ;Personality trait is the central part of human behavior. Social networking sites integrate all kinds of personal information, which are related to personality traits. Through personality traits to understand different groups, in order to improve the effectiveness and even personalization of advertising, promotion, recommendation and other marketing purposes, it also helps enterprises to recruit talents, measure work performance, or other purposes.
    In color psychology, color preference is considered to be the key to affect a person′s potential personality. In the past, the research on judging personality traits from the color of users′ photos on social networking sites has not yet linked the photos and personality traits of social networking sites with the application of color proposed by color psychology, Therefore, this study wants to explore whether we can better understand personality traits through the perspective of color psychology; In addition, previous studies used the average value of hue as the input of image color, which was refuted by other studies. Therefore, this study hypothesized that the dominant color of a single image with the most color components could better distinguish the main areas in the image.
    In this study, 1080 photos on social networking sites were collected. The main colors of the photos were extracted and connected by color psychology. Then SVM and random forest were used to train the prediction model and predict the personality traits of the subjects.
    The results of the experiment firstly confirmed that color preference affects personality traits according to color psychology; Secondly, the main tone of the photo can predict personality traits, and the best prediction accuracy of random forest is 0.95; The most important finding is that when using dataset 1, the prediction accuracy can be greatly improved.
    顯示於類別:[企業管理研究所] 博碩士論文

    文件中的檔案:

    檔案 描述 大小格式瀏覽次數
    index.html0KbHTML78檢視/開啟


    在NCUIR中所有的資料項目都受到原著作權保護.

    社群 sharing

    ::: Copyright National Central University. | 國立中央大學圖書館版權所有 | 收藏本站 | 設為首頁 | 最佳瀏覽畫面: 1024*768 | 建站日期:8-24-2009 :::
    DSpace Software Copyright © 2002-2004  MIT &  Hewlett-Packard  /   Enhanced by   NTU Library IR team Copyright ©   - 隱私權政策聲明