LLM-Based Behavior Prediction for Social Media Users with Continuous Memory

ACL ARR 2025 July Submission351 Authors

Abstract: Large language models (LLMs) have demonstrated strong capabilities in simulating social roles and generating human-like behaviors. However, their effectiveness in predicting real-world user behavior under continuous memory accumulation remains largely unexplored. Most existing studies focus on short-term interactions or static personas, neglecting the dynamic nature of users' historical experiences in social media environments. To address this gap, we introduce FineRob, a novel dataset for fine-grained behavior prediction of social media users, which includes long-term memory traces from 1,866 users across three platforms. Each behavior is decomposed into three elements: object, type, and content, resulting in 78.6k QA records.We identify that as memory accumulates, prediction accuracy drops significantly due to the model's difficulty in accessing detailed historical information. We further propose the OM-CoT fine-tuning framework to enhance the model's ability to process and utilize long-term memory. Experimental results show that our method effectively reduces the performance degradation caused by memory growth, improving fine-grained behavior prediction. \footnote{Code and dataset are available at \url{https://anonymous.4open.science/r/FineRob-791B/}}.

Paper Type: Long

Research Area: NLP Applications

Research Area Keywords: LLM,Social Media,User behavior Prediction,Long Memory

Contribution Types: NLP engineering experiment, Data resources

Languages Studied: English,Chinese

Reassignment Request Area Chair: This is not a resubmission

Reassignment Request Reviewers: This is not a resubmission

A1 Limitations Section: This paper has a limitations section.

A2 Potential Risks: Yes

A2 Elaboration: Section Ethics Statement

B Use Or Create Scientific Artifacts: Yes

B1 Cite Creators Of Artifacts: Yes

B1 Elaboration: section Experiment Settings

B2 Discuss The License For Artifacts: Yes

B2 Elaboration: section Experiment Settings

B3 Artifact Use Consistent With Intended Use: Yes

B3 Elaboration: section Experiment Settings

B4 Data Contains Personally Identifying Info Or Offensive Content: Yes

B4 Elaboration: section Ethics Statement

B5 Documentation Of Artifacts: Yes

B5 Elaboration: section Experiment Settings

B6 Statistics For Data: Yes

B6 Elaboration: section FineRob Dataset

C Computational Experiments: Yes

C1 Model Size And Budget: Yes

C1 Elaboration: section Experiment Settings

C2 Experimental Setup And Hyperparameters: Yes

C2 Elaboration: section Experiment Settings

C3 Descriptive Statistics: Yes

C3 Elaboration: section Main Result

C4 Parameters For Packages: Yes

C4 Elaboration: section Experiment Settings

D Human Subjects Including Annotators: No

D1 Instructions Given To Participants: N/A

D2 Recruitment And Payment: N/A

D3 Data Consent: Yes

D3 Elaboration: section Experiment Settings

D4 Ethics Review Board Approval: N/A

D5 Characteristics Of Annotators: N/A

E Ai Assistants In Research Or Writing: Yes

E1 Information About Use Of Ai Assistants: No

E1 Elaboration: AI-assisted polishing

Author Submission Checklist: yes

Submission Number: 351