Analyzing Connections Between User Attributes, Images, and Text

被引:0
|
作者
Laura Burdick
Rada Mihalcea
Ryan L. Boyd
James W. Pennebaker
机构
[1] University of Michigan,Department of Computer Science and Engineering
[2] Lancaster University,Department of Psychology
[3] The University of Texas at Austin,Department of Psychology
来源
Cognitive Computation | 2021年 / 13卷
关键词
Personality; Gender; Natural language processing; Computer vision; Computational social science;
D O I
暂无
中图分类号
学科分类号
摘要
This work explores the relationship between a person’s demographic/psychological traits (e.g., gender and personality) and self-identity images and captions. We use a dataset of images and captions provided by N ≈ 1350 individuals, and we automatically extract features from both the images and captions. We identify several visual and textual properties that show reliable relationships with individual differences between participants. The automated techniques presented here allow us to draw interesting conclusions from our data that would be difficult to identify manually, and these techniques are extensible to other large datasets. Additionally, we consider the task of predicting gender and personality using both single modality features and multimodal features. We show that a multimodal predictive approach outperforms purely visual methods and purely textual methods. We believe that our work on the relationship between user characteristics and user data has relevance in online settings, where users upload billions of images each day.
引用
收藏
页码:241 / 260
页数:19
相关论文
共 50 条
  • [21] Analyzing the relationship between text features and grants productivity
    Tohalino, Jorge A. V.
    Quispe, Laura V. C.
    Amancio, Diego R.
    SCIENTOMETRICS, 2021, 126 (05) : 4255 - 4275
  • [22] Integrating words, images, and text in BMGIM: Finding connections through semiotic intertextuality
    Short, Alison
    Gibb, Heather
    Holmes, Colin
    NORDIC JOURNAL OF MUSIC THERAPY, 2011, 20 (01): : 3 - 21
  • [23] The Relationship between Online Social Network Ties and User Attributes
    Mahmoudi, Amin
    Yaakub, Mohd Ridzwan
    Abu Bakar, Azuraliza
    ACM TRANSACTIONS ON KNOWLEDGE DISCOVERY FROM DATA, 2019, 13 (03)
  • [24] Interactions between images, text and sound in translation
    Garcia Jimenez, Rocio
    Garcia Luque, Francisca
    Jimenez Carra, Nieves
    TRANS-REVISTA DE TRADUCTOLOGIA, 2020, (24): : 15 - 16
  • [25] INTERRELATIONS BETWEEN PERCEIVED ATTRIBUTES AND THEIR INFLUENCE ON PREFERENCE OF USER INTERFACES
    Eytam, Eleanor
    GLOBAL AND NATIONAL BUSINESS THEORIES AND PRACTICE: BRIDGING THE PAST WITH THE FUTURE, 2017, : 2106 - 2107
  • [26] Analyzing User Reviews on Digital Detox Apps: A Text Mining and Sentiment Analysis Approach
    Khan, Nazar Fatima
    Khan, Mohammed Naved
    JOURNAL OF CONSUMER BEHAVIOUR, 2025, 24 (01) : 392 - 404
  • [28] Analyzing correlation between trust and user similarity in online communities
    Ziegler, CN
    Lausen, G
    TRUST MANAGEMENT, PROCEEDING, 2004, 2995 : 251 - 265
  • [29] Social Circle Discovery in Ego-Networks by Mining the Latent Structure of User Connections and Profile Attributes
    Petkos, Georgios
    Papadopoulos, Symeon
    Kompatsiaris, Yiannis
    PROCEEDINGS OF THE 2015 IEEE/ACM INTERNATIONAL CONFERENCE ON ADVANCES IN SOCIAL NETWORKS ANALYSIS AND MINING (ASONAM 2015), 2015, : 880 - 887
  • [30] From Face Images and Attributes to Attributes
    Torfason, Robert
    Agustsson, Eirikur
    Rothe, Rasmus
    Timofte, Radu
    COMPUTER VISION - ACCV 2016, PT III, 2017, 10113 : 313 - 329