Recall results of four algorithms.

<div><p>Aiming at the problem that traditional network public opinion monitoring and searching are inefficient and can easily cause resource waste, the study firstly, through the dynamic deletion-shortest path algorithm to classify network text, and on this basis, innovatively constructs...

Full description

Saved in:
Bibliographic Details
Main Author: Nan Xu (107466) (author)
Other Authors: Yifeng Wang (117830) (author)
Published: 2024
Subjects:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1852025129835429888
author Nan Xu (107466)
author2 Yifeng Wang (117830)
author2_role author
author_facet Nan Xu (107466)
Yifeng Wang (117830)
author_role author
dc.creator.none.fl_str_mv Nan Xu (107466)
Yifeng Wang (117830)
dc.date.none.fl_str_mv 2024-11-18T18:30:22Z
dc.identifier.none.fl_str_mv 10.1371/journal.pone.0310894.t001
dc.relation.none.fl_str_mv https://figshare.com/articles/dataset/Recall_results_of_four_algorithms_/27848158
dc.rights.none.fl_str_mv CC BY 4.0
info:eu-repo/semantics/openAccess
dc.subject.none.fl_str_mv Genetics
Science Policy
Biological Sciences not elsewhere classified
Mathematical Sciences not elsewhere classified
Information Systems not elsewhere classified
shortest path algorithm
research results show
recurrent neural network
public opinion risk
convolutional neural network
classification effect measurement
average precision rate
30 %, 79
uses attention mechanism
hybrid dynamic deletion
div >< p
sentiment classification model
classify network text
dynamic deletion
attention mechanism
recall rate
long text
classification speed
classification model
84 %,
55 %,
53 %,
superior performance
innovatively constructs
decision model
dc.title.none.fl_str_mv Recall results of four algorithms.
dc.type.none.fl_str_mv Dataset
info:eu-repo/semantics/publishedVersion
dataset
description <div><p>Aiming at the problem that traditional network public opinion monitoring and searching are inefficient and can easily cause resource waste, the study firstly, through the dynamic deletion-shortest path algorithm to classify network text, and on this basis, innovatively constructs a text sentiment classification model based on the variant of convolutional neural network and recurrent neural network, and secondly, uses attention mechanism to classify the model. improvement of the classification model by using the attention mechanism. The research results show that the average precision rate, recall rate, and F-value of the dynamic deletion-shortest path algorithm are 97.30%, 79.55%, and 87.53%, and the classification speed is 397 <i>KB</i>/<i>s</i>, which is better than the traditional shortest path algorithm. In the classification effect measurement of long text, the accuracy and F-value of the recurrent neural network variant model are above 84%, and the accuracy of the text sentiment classification model with the introduction of the attention mechanism is improved by 3.89% compared to the pre-improvement period. In summary, the dynamic deletion-shortest path algorithm proposed in the study and the sentiment classification model with the introduction of the attention mechanism have superior performance and can provide certain application value for campus social network opinion risk decision-making.</p></div>
eu_rights_str_mv openAccess
id Manara_42e2c09f37bf7551e199ddcf07d638b1
identifier_str_mv 10.1371/journal.pone.0310894.t001
network_acronym_str Manara
network_name_str ManaraRepo
oai_identifier_str oai:figshare.com:article/27848158
publishDate 2024
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
rights_invalid_str_mv CC BY 4.0
spelling Recall results of four algorithms.Nan Xu (107466)Yifeng Wang (117830)GeneticsScience PolicyBiological Sciences not elsewhere classifiedMathematical Sciences not elsewhere classifiedInformation Systems not elsewhere classifiedshortest path algorithmresearch results showrecurrent neural networkpublic opinion riskconvolutional neural networkclassification effect measurementaverage precision rate30 %, 79uses attention mechanismhybrid dynamic deletiondiv >< psentiment classification modelclassify network textdynamic deletionattention mechanismrecall ratelong textclassification speedclassification model84 %,55 %,53 %,superior performanceinnovatively constructsdecision model<div><p>Aiming at the problem that traditional network public opinion monitoring and searching are inefficient and can easily cause resource waste, the study firstly, through the dynamic deletion-shortest path algorithm to classify network text, and on this basis, innovatively constructs a text sentiment classification model based on the variant of convolutional neural network and recurrent neural network, and secondly, uses attention mechanism to classify the model. improvement of the classification model by using the attention mechanism. The research results show that the average precision rate, recall rate, and F-value of the dynamic deletion-shortest path algorithm are 97.30%, 79.55%, and 87.53%, and the classification speed is 397 <i>KB</i>/<i>s</i>, which is better than the traditional shortest path algorithm. In the classification effect measurement of long text, the accuracy and F-value of the recurrent neural network variant model are above 84%, and the accuracy of the text sentiment classification model with the introduction of the attention mechanism is improved by 3.89% compared to the pre-improvement period. In summary, the dynamic deletion-shortest path algorithm proposed in the study and the sentiment classification model with the introduction of the attention mechanism have superior performance and can provide certain application value for campus social network opinion risk decision-making.</p></div>2024-11-18T18:30:22ZDatasetinfo:eu-repo/semantics/publishedVersiondataset10.1371/journal.pone.0310894.t001https://figshare.com/articles/dataset/Recall_results_of_four_algorithms_/27848158CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/278481582024-11-18T18:30:22Z
spellingShingle Recall results of four algorithms.
Nan Xu (107466)
Genetics
Science Policy
Biological Sciences not elsewhere classified
Mathematical Sciences not elsewhere classified
Information Systems not elsewhere classified
shortest path algorithm
research results show
recurrent neural network
public opinion risk
convolutional neural network
classification effect measurement
average precision rate
30 %, 79
uses attention mechanism
hybrid dynamic deletion
div >< p
sentiment classification model
classify network text
dynamic deletion
attention mechanism
recall rate
long text
classification speed
classification model
84 %,
55 %,
53 %,
superior performance
innovatively constructs
decision model
status_str publishedVersion
title Recall results of four algorithms.
title_full Recall results of four algorithms.
title_fullStr Recall results of four algorithms.
title_full_unstemmed Recall results of four algorithms.
title_short Recall results of four algorithms.
title_sort Recall results of four algorithms.
topic Genetics
Science Policy
Biological Sciences not elsewhere classified
Mathematical Sciences not elsewhere classified
Information Systems not elsewhere classified
shortest path algorithm
research results show
recurrent neural network
public opinion risk
convolutional neural network
classification effect measurement
average precision rate
30 %, 79
uses attention mechanism
hybrid dynamic deletion
div >< p
sentiment classification model
classify network text
dynamic deletion
attention mechanism
recall rate
long text
classification speed
classification model
84 %,
55 %,
53 %,
superior performance
innovatively constructs
decision model