MétaCan
Menu
Back to cohort
Record W4403636007 · doi:10.1109/access.2024.3484578

QuickCharNet: An Efficient URL Classification Framework for Enhanced Search Engine Optimization

2024· article· en· W4403636007 on OpenAlexaff
Fardin Rastakhiz, Mahdi Eftekhari, Sahar Vahdati

Bibliographic record

VenueIEEE Access · 2024
Typearticle
Languageen
FieldComputer Science
TopicSpam and Phishing Detection
Canadian institutionsArtificial Intelligence in Medicine (Canada)
FundersMinistry of Education and Research, RomaniaBundesministerium für Bildung und Forschung
KeywordsComputer scienceSearch engineSpamdexingSearch engine optimizationInformation retrievalWeb search queryMetasearch engine

Abstract

fetched live from OpenAlex

The uniform resource locator (URL) conveys essential information about a page’s topic, authority, and security, which significantly influences its ranking in search engine results. However, many existing URL classification methods used for real-time online inference face challenges related to time and memory complexity during preprocessing, processing, and inference stages. In environments where quick decision-making is crucial, such as cybersecurity or digital marketing, slow or resource-intensive classification processes can limit the ability to prioritize and select URLs effectively. This study presents QuickCharNet, a novel URL classification architecture that combines character-level convolution with token-level representation to improve efficiency and generalizability for real-time URL inference. Key contributions of QuickCharNet include the use of max and mean pooling techniques to aggregate character embeddings into token embeddings, the exploration of sub-word tokenizers for optimal URL representation, and a comparative analysis of five models using metrics such as accuracy, F1-Score, and t-distributed Stochastic Neighbor Embedding (t-SNE) visualizations. By prioritizing user experience and safety, this research aims to enhance the accuracy of topic classification based on URL positioning in search engine results and evaluate the likelihood of spam. Ultimately, the findings support developers in efficiently identifying and addressing URL-related issues for improved search engine optimization. QuickCharNet was trained on a dataset developed for this study and two benchmark datasets. Experiments revealed optimal settings for URL classification and spam detection, resulting in a 4.92% improvement in topic classification and a 1% improvement in spam detection. These results emphasize the significance of URLs in search engine optimization: well-named URLs enable better topic classification, increasing the likelihood of appearing on the first page of search engine results by 4.92%. Conversely, URLs identified as spam face a higher chance of lower rankings, impacting their first-page visibility by 1%. Link to the source codes: <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://github.com/FardinRastakhiz/QuickCharNet</uri>.

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 score0.879
Threshold uncertainty score0.981

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0000.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.001
Science and technology studies0.0000.000
Scholarly communication0.0010.001
Open science0.0010.000
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 head0.067
GPT teacher head0.367
Teacher spread0.300 · 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

Citations5
Published2024
Admission routes1
Has abstractyes

Explore more

Same venueIEEE AccessSame topicSpam and Phishing DetectionFrench-language works237,207