MétaCan
Menu
Back to cohort
Record W4231125000 · doi:10.32920/ryerson.14648478

Distributed recommender system using multi-agent for social networks

2021· preprint· en· W4231125000 on OpenAlexafffund
Lubaid Ahmed

Bibliographic record

Venuenot available
Typepreprint
Languageen
FieldComputer Science
TopicSpam and Phishing Detection
Canadian institutionsToronto Metropolitan University
FundersUniversity of Ottawa
KeywordsRecommender systemComputer scienceScalabilityCosine similarityExploitProcess (computing)Social network (sociolinguistics)Web crawlerCluster analysisSimilarity (geometry)World Wide WebInformation retrievalSocial mediaArtificial intelligenceDatabaseComputer security

Abstract

fetched live from OpenAlex

Social networks have become significant tools due to the vast and useful information existing in them. The social platforms also act as the storage of entered choices of millions of users for various applications such as political surveys, research studies, marketing product preferences and many more. Social network recommender systems exploit this information and direct users in selecting their choices. It is clear that recommender systems should be efficient enough to be able to process the huge magnitude of data that has been generated in recent years by social network users. This research proposes a foundation of an efficient and scalable recommender system to be able to process large amount of data (i.e. Big data) in a short amount of time. The main goal is providing scalability and efficiency of the recommender system. The simulation of the prototype of such a distributed recommender system by using multi-agent based technologies shows promising results. These prototypes provide recommendations to users about other users with the similar interests in online and distributed manner as real recommender systems. The agents can simulate users or can be used as the containers of algorithms for comparing the similarity between users by different approaches, such as cosine similarity and clustering methods for testing and examining real scenarios. To be able to test these prototypes in agent-based simulation environment an agent-based framework is developed. This framework has three modules named social network crawler, social network simulator and employed prototype of the distributed recommender system that use different text and data mining algorithms. Finally, newly developed performance metric (called Scalability Factor) is introduced that shows the minimum number of servers needed to be able to run the agent systems in parallel. This thesis shows using a distributed and parallel model for recommender systems is the key to increase the speed of recommendation convergence and as a result to provide scalability. Multi-agent based simulation results, coupled with numerical analysis affirm that the proposed solution provides scalability and efficiency for recommender systems.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.000
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: Simulation or modeling
GenreCandidate signal: Methods · Consensus signal: none
Teacher disagreement score0.807
Threshold uncertainty score0.915

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0000.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.000
Science and technology studies0.0000.000
Scholarly communication0.0010.000
Open science0.0010.001
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0000.000

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.114
GPT teacher head0.312
Teacher spread0.198 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one teacher head, not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designSimulation or modeling
Domainnot available
GenreMethods

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations2
Published2021
Admission routes2
Has abstractyes

Explore more

Same topicSpam and Phishing DetectionFrench-language works237,207