Comparative analysis of TF-IDF and loglikelihood method for keywords extraction of twitter data

Abid, Muhammad Adeel; Mushtaq, Muhammad Faheem; Akram, Urooj; Abbasi, Mateen Ahmed; Rustam, Furqan

doi:10.22581/muet1982.2301.09

Cited by 4 publications

(2 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This study uses decision trees, random forests, support vector machines, logistic regression, Gaussian Naïve Bayes and XGBoost. Different train-test splits of the dataset are used to train tmachine learning models [39]. Description of machine learning classifiers along with the calculation formula is given below.…”

Section: ) Machine Learning Algorithmsmentioning

confidence: 99%

IoT-Based Smart Biofloc Monitoring System for Fish Farming Using Machine Learning

Abid,

Amjad,

Munir

et al. 2024

IEEE Access

View full text Add to dashboard Cite

Biofloc technology assists in increasing the sustainability of fish farming by reusing and recycling waste water. However, its sophisticated operation makes it very sensitive to environmental conditions. A slight disturbance in one or more parameters can lead to high fish mortality and loss. IoT systems provide an efficient way of closely monitoring the biofloc to avoid catastrophe. The best aqua conditions vary depending on the fish. Therefore, there is a strong need to explore ideal conditions for different fishes. In this work, we have focused on Tilapi fish in the southern Punjab region to find the most suitable parameters. We have developed an IoT solution for monitoring Biofloc and gathering data. We have used low-cost sensors in our product to make it feasible for poor fish farmers. Multiple machine learning algorithms such as decision trees, random forest, support vector machine, logistic regression, Gaussian naive Bayes, XGBoost and ensemble learning are applied to the collected dataset to effectively predict mortality. Our analysis exhibits that the random forest and XGBoost achieved 98% accuracy in estimating mortality. The union of IoT, machine learning, and affordability positions our study at the forefront of advancing sustainable aquaculture practices in southern Punjab, Pakistan.

show abstract

Section: ) Machine Learning Algorithmsmentioning

confidence: 99%

IoT-Based Smart Biofloc Monitoring System for Fish Farming Using Machine Learning

Abid,

Amjad,

Munir

et al. 2024

IEEE Access

View full text Add to dashboard Cite

show abstract

“…The TF-IDF method is a statistical method for assessing how often a word appears in a document [10], the TF-IDF is a simple approach with good accuracy [11]. TF-IDF can be used to analyze words that often appear in research titles so that they can find ideas for research titles and the right naming of titles.…”

mentioning

confidence: 99%

Analysis of Frequently Appearing Words in the Titles of 2023 Research Grant Winners in Indonesia Using the TF-IDF Method

Setiawan,

Kisman,

Imam

2023

J. Inf. Syst. Informatics

View full text Add to dashboard Cite

Research activities are an obligation to be carried out by a lecturer, each year the Government of Indonesia through the Ministry of Education, Culture, Research and Technology encourages the improvement of research through a large amount of research funding aid through several schemes of grant competition. By 2023, the percentage of proposals funded was only 22.7% of the total of research proposals submitted as 28.404. One of the problems that arises for the lecturer who follows the research grant is to determine the title of the research. The research aims to identify the words that often appear on the research titles that escape funding from each grant scheme by performing word grinding using the TF-IDF method. The results of this research indicate that in the novice lecturer research grant scheme (PDP) the word that often appears is the word "based" with a total of 434 proposals, in the regular fundamental research (PFR) the word that often appears is "development" of 374 proposals , domestic cooperation research (PKDN) the word that often appears is "based" with 117 proposals, post-graduate research doctoral dissertation research (PPS-PDD) the word that often appears is "model" with 154 proposals, in post-graduate research master's thesis research (PTS-PTM) words that often appear "based" are 191 proposals and in the downstream applied research scheme (PT-JH) words that often appear "based" are 82 proposals. This research can provide an overview of the names of titles funded based on the highest number of occurrences of a word from all titles funded. The words "based", "development" and "model" are the 3 largest words that appear in the titles of proposals funded in the PFR, PKDN, PPS-PDD, PPS-PTM, and PT-JH schemes. For the PDP scheme, the order of the 3 largest words that appear in the title of the proposal is "based", "regency", and "development".

show abstract

Deep-KeywordNet: automated english keyword extraction in documents using deep keyword network based ranking

Khatun,

Sarkar

2024

Multimed Tools Appl

View full text Add to dashboard Cite

Comparative analysis of TF-IDF and loglikelihood method for keywords extraction of twitter data

Cited by 4 publications

References 16 publications

IoT-Based Smart Biofloc Monitoring System for Fish Farming Using Machine Learning

IoT-Based Smart Biofloc Monitoring System for Fish Farming Using Machine Learning

Analysis of Frequently Appearing Words in the Titles of 2023 Research Grant Winners in Indonesia Using the TF-IDF Method

Deep-KeywordNet: automated english keyword extraction in documents using deep keyword network based ranking

Contact Info

Product

Resources

About