Improve topic modeling algorithms based on Twitter hashtags

Hayder M. Alash

doi:10.1088/1742-6596/1660/1/012100

Details

Publication Date

Sun Nov 01 2020

Journal Name

Journal Of Physics: Conference Series

Volume

1660

DOI

10.1088/1742-6596/1660/1/012100

Choose Citation Style

Statistics

View publication

6

Statistics

(20)

(19)

Improve topic modeling algorithms based on Twitter hashtags

Hayder M. Alash

...Show More Authors

Abstract<p>Today with increase using social media, a lot of researchers have interested in topic extraction from Twitter. Twitter is an unstructured short text and messy that it is critical to find topics from tweets. While topic modeling algorithms such as Latent Semantic Analysis (LSA) and Latent Dirichlet Allocation (LDA) are originally designed to derive topics from large documents such as articles, and books. They are often less efficient when applied to short text content like Twitter. Luckily, Twitter has many features that represent the interaction between users. Tweets have rich user-generated hashtags as keywords. In this paper, we exploit the hashtags feature to improve topics learned from Twitter content without modifying the basic topic model of LSA and LDA. Users who share the same hashtag at most discuss the same topic. We compare the performance of the two methods (LSA and LDA) using the topic coherence (with and without hashtags). The experiment result on the Twitter dataset showed that LSA has better coherence score with hashtags than that do not incorporate hashtags. In contrast, our experiments show that the LDA has a better coherence score without incorporating hashtags. Finally, LDA has a better coherence score than LSA and the best coherence result obtained from the LDA method was (0.6047) and the LSA method was (0.4744) but the number of topics in LDA was higher than LSA. Thus, LDA may cause the same tweets to discuss the same subject set into different clustering.</p>

View Publication

Publication Date

Mon Feb 13 2023

Journal Name

Journal Of Educational And Psychological Researches

Evaluation of English Language Textbooks for Fifth and Sixth Graders Based on the American Council Criteria for Teaching Foreign Languages (ACTFL)

evaluation

standards

fifth and sixth graders

American council criteria for teaching foreign languages (ACTFL)

Mona

Muhammed

...Show More Authors

Abstract

This study aims to identify the extent to which the criteria of the American Council for Teaching Foreign Languages (ACTFL) are included in the English language books for the fifth and sixth graders. To achieve the objective of the study, a content analysis card was prepared, where the classification of language proficiencies was divided into five main levels (beginner, intermediate, advanced, superior, and distinguished) of the four language skills (listening, speaking, reading, and writing), The content analysis card consisted of (89) indicators distributed at the four levels of language skills as follows: Listening (17), speaking (33), reading (15), and writing (26). The study sample consisted of Engl

View Publication Preview PDF

Publication Date

Sun Dec 01 2024

Journal Name

Russian Journal Of General Chemistry

Synthesis, Characterization, and Biological Evaluation for New Derivatives Based on 2Сhloro-N-[4-(5-phenyl-1,3,4-oxadiazol-2-yl)phenyl]acetamide

N. M.

K. A.

H. A.

J. H.

H. S.

R. K.

...Show More Authors

View Publication

(2)

Publication Date

Thu Dec 30 2021

Journal Name

Periodicals Of Engineering And Natural Sciences (pen)

Design a system for an approved video copyright over cloud based on biometric iris and random walk generator using watermark technique

Azeez R.A.

...Show More Authors

View Publication

(54)

(12)

Publication Date

Mon Aug 05 2024

Journal Name

Food And Bioprocess Technology

Development of an Innovative Reinforced Food Packaging Film Based on Corn Starch/Hydroxypropyl Methylcellulose/Nanocrystalline Cellulose Incorporated with Nanogel Containing Quercetin

Hanan Adnan Shaker

Nazila

Dhuha K.

Mastafa H.

Vahid

Sumyah Hasan

Marjan

...Show More Authors

View Publication

(12)

(9)

Publication Date

Sun Dec 01 2024

Journal Name

Russian Journal Of General Chemistry

Synthesis, Characterization, and Biological Evaluation for New Derivatives Based on 2Сhloro-N-[4-(5-phenyl-1,3,4-oxadiazol-2-yl)phenyl]acetamide

N. M.

K. A.

H. A.

J. H.

H. S.

R. K.

...Show More Authors

View Publication

(2)

Publication Date

Wed May 01 2024

Journal Name

Journal Of Drug Delivery Science And Technology

Antibacterial and wound healing performance of a novel electrospun nanofibers based on polymethyl-methacrylate/gelatin impregnated with different content of propolis

Basma

Elham

Hanan

Mastafa H.

Iman Bahjat Namuq

Soghra

Marjan

Fatemeh

...Show More Authors

View Publication

(13)

(8)

Publication Date

Sat Nov 01 2025

Journal Name

Russian Journal Of General Chemistry

Synthesis, Antibacterial Activity, and Molecular Docking Study of Some New Azo Derivatives Based on 2(4-Aminophenyl)-5-Substituted 1,3,4-Oxadiazole

I. A. A.

Jumbad H.

...Show More Authors

View Publication

Publication Date

Fri Oct 02 2020

Journal Name

International Journal Of Pharmaceutical Research

A turbidimetric method for the quantitative determination of cyproheptadine hydrochloride in tablets using an optoelectronic detector based on the LEDs array

Flow injection analysis

Turbidity

Cyproheptadine hydrochloride (CPH)

Pharmaceutical preparations

Quality control analysis.

Jalal N.

...Show More Authors

View Publication Preview PDF

(17)

(2)

Publication Date

Sun Dec 01 2024

Journal Name

Russian Journal Of General Chemistry

Synthesis, Characterization, and Biological Evaluation for New Derivatives Based on 2Сhloro-N-[4-(5-phenyl-1,3,4-oxadiazol-2-yl)phenyl]acetamide

N. M.

K. A.

H. A.

J. H.

H. S.

R. K.

...Show More Authors

(2)

Publication Date

Sat Feb 09 2019

Journal Name

Journal Of The College Of Education For Women

Hybrid Transform Based Denoising with Block Thresholding

Iman M.G.

...Show More Authors

A frequently used approach for denoising is the shrinkage of coefficients of the noisy signal representation in a transform domain. This paper proposes an algorithm based on hybrid transform (stationary wavelet transform proceeding by slantlet transform); The slantlet transform is applied to the approximation subband of the stationary wavelet transform. BlockShrink thresholding technique is applied to the hybrid transform coefficients. This technique can decide the optimal block size and thresholding for every wavelet subband by risk estimate (SURE). The proposed algorithm was executed by using MATLAB R2010aminimizing Stein’s unbiased with natural images contaminated by white Gaussian noise. Numerical results show that our algorithm co

View Publication Preview PDF

1 2 ... 105 106 107 108 ... 722 723