Optimizing user profile matching: a text-based approach

Abstract

The rapid expansion of social media platforms has made linking user profiles across various networks an essential aspect of maintaining a consistent identity. With 4.66 billion users reported to be in the Websphere, many are active on multiple social media platforms simultaneously. Identifying users across multiple platforms poses challenges in integrating user profiles from various sources. Different matching schemes have been suggested over the years based on different user profile features, but very little information has been uncovered about user-generated text as a unique attribute for user profile matching, which generally poses real challenges in real-world scenarios. As many users have insufficient text and the use of non-discrete text information makes the comparison operation between the two social networks of quadratic complexity. Our study examines the different existing literature schemes for matching user profile pairs based only on their generated textual content. We suggest and evaluate the effectiveness of a two stage matching approach based on Locality Sensitive Hashing clustering and nearest neighbor search. We also present other matching results of different user representations language models and matching schemes.

Keywords:

• Profile linkage
• Usergenerated content
• Text mining
• Social networks

Disclosure statement

No potential conflict of interest was reported by the author(s).

Notes

1 https://www.pewresearch.org/internet/2021/04/07/social-media-use-in-2021/.

2 Also called alternatively as User Matching (UM) or User Identity Matching (UIM) and Profile Alignment.

Additional information

Notes on contributors

Youcef Benkhedda

Youcef Benkhedda is a PhD Student at ESI (École Nationale Supérieure d’Informatique) specializing in topics related to online user profiling, online community detection, and general computational science. He is actively involved in research and exploration of various aspects of user behavior and interaction in online platforms. His work focuses on understanding how users create and engage with content, as well as developing computational models and algorithms to analyze and extract meaningful insights from large-scale user data.

Faical Azouaou

Faical Azouaou is a researcher who has made significant contributions in various areas of computational science and natural language processing. He has published several papers on topics such as Arabic natural language processing, sentiment analysis, semantic annotation, and ontology matching. His research has focused on developing tools and techniques to analyze and understand Arabic text, including dialect identification and sentiment analysis. Azouaou has also worked on projects related to education, developing annotation tools for teachers and exploring the use of ontologies in e-learning.