A Comparison of Lexicon-Based and ML-Based Sentiment Analysis: Are There Outlier Words? DOI

Siddhant Jaydeep Mahajani,

Shashank Srivastava, Alan F. Smeaton

и другие.

Опубликована: Дек. 7, 2023

Lexicon-based approaches to sentiment analysis of text are based on each word or lexical entry having a predefined weight indicating its polarity. These usually man-ually assigned but the accuracy these when compared against machine leaning computing sentiment, not known. It may be that there entries whose values cause lexicon-based approach give results which very different learning approach. In this paper we compute for more than 150,000 English language texts drawn from 4 domains using Hedonometer, technique and Azure, contemporary machine-learning is part Azure Cognitive Services family APIs easy use. We model differences in scores between documents domain regression analyse independent variables (Hedonometer entries) as indicators word's importance contribution score differences. Our findings depends no standout systematically scores.

Язык: Английский

"Challenges and future in deep learning for sentiment analysis: a comprehensive review and a proposed novel hybrid approach" DOI Creative Commons
Md Shofiqul Islam, Muhammad Nomani Kabir, Ngahzaifa Ab Ghani

и другие.

Artificial Intelligence Review, Год журнала: 2024, Номер 57(3)

Опубликована: Фев. 19, 2024

Abstract Social media is used to categorise products or services, but analysing vast comments time-consuming. Researchers use sentiment analysis via natural language processing, evaluating methods and results conventionally through literature reviews assessments. However, our approach diverges by offering a thorough analytical perspective with critical analysis, research findings, identified gaps, limitations, challenges future prospects specific deep learning-based in recent times. Furthermore, we provide in-depth investigation into categorizing prevalent data, pre-processing methods, text representations, learning models, applications. We conduct evaluation of advances architectures, assessing their pros cons. Additionally, offer meticulous methodologies, integrating insights on applied tools, strengths, weaknesses, performance results, detailed feature-based examination. present discussion the challenges, drawbacks, factors contributing successful enhancement accuracy within realm analysis. A comparative article clearly shows that capsule-based RNN approaches give best an 98.02% which CNN RNN-based models. implemented various advanced deep-learning models across four benchmarks identify top performers. introduced innovative CRDC (Capsule Deep Bi structured RNN) model, demonstrated superior compared other methods. Our proposed achieved remarkable different databases: IMDB (88.15%), Toxic (98.28%), CrowdFlower (92.34%), ER (95.48%). Hence, this method holds promise for automated potential deployment.

Язык: Английский

Процитировано

20
Dynamic fitness-distance balance-based artificial rabbits optimization algorithm to solve optimal power flow problem DOI
Hüseyin Bakır

Expert Systems with Applications, Год журнала: 2023, Номер 240, С. 122460 - 122460

Опубликована: Ноя. 9, 2023

Язык: Английский

Процитировано

28
Enhanced Artificial Rabbits Algorithm Integrating Equilibrium Pool to Support PV Power Estimation via Module Parameter Identification DOI Creative Commons
Idris H. Smaili, Ghareeb Moustafa, Dhaifallah R. Almalawi

и другие.

International Journal of Energy Research, Год журнала: 2024, Номер 2024(1)

Опубликована: Янв. 1, 2024

This paper proposes a novel innovative version of enhanced artificial rabbit optimization (EARO) algorithm integrating an equilibrium pool (EP) that consists the best solutions. Furthermore, detour foraging and hiding mechanisms are modified to amplify search capability. These modifications enable dynamically focus on exploring various randomized directions emanating from EP. The proposed EARO is designed investigate PV module characteristics identification issue. To obtain nine parameters triple diode model (TDM) while taking into account three distinct real‐world modules, utilized evaluated in comparison with standard ARO. tested different modules: Ultra 85‐P panel, PVM_752GaAs, RTC France. results corresponding compared respect several published latest studies. simulation show shows significant overall improvement rates for each modules. A validation common SDM DDM France assessed which illustrates superiority robustness over recent results.

Язык: Английский

Процитировано

8
A review on emotion detection by using deep learning techniques DOI Creative Commons

Tulika Chutia,

Nomi Baruah

Artificial Intelligence Review, Год журнала: 2024, Номер 57(8)

Опубликована: Июль 11, 2024

Abstract Along with the growth of Internet its numerous potential applications and diverse fields, artificial intelligence (AI) sentiment analysis (SA) have become significant popular research areas. Additionally, it was a key technology that contributed to Fourth Industrial Revolution (IR 4.0). The subset AI known as emotion recognition systems facilitates communication between IR 4.0 5.0. Nowadays users social media, digital marketing, e-commerce sites are increasing day by resulting in massive amounts unstructured data. Medical, public safety, education, human resources, business, other industries also use system widely. Hence provides large amount textual data extract emotions from them. paper presents systematic literature review existing published 2013 2023 text-based detection. This scrupulously summarized 330 papers different conferences, journals, workshops, dissertations. explores approaches, methods, deep learning models, aspects, description datasets, evaluation techniques, Future prospects learning, challenges studies limitations practical implications.

Язык: Английский

Процитировано

7
Modified artificial rabbits optimization combined with bottlenose dolphin optimizer in feature selection of network intrusion detection DOI Creative Commons

Fukui Li,

Hui Xu, Feng Qiu

и другие.

Electronic Research Archive, Год журнала: 2024, Номер 32(3), С. 1770 - 1800

Опубликована: Янв. 1, 2024

<p>For the feature selection of network intrusion detection, issue numerous redundant features arises, posing challenges in enhancing detection accuracy and adversely affecting overall performance to some extent. Artificial rabbits optimization (ARO) is capable reducing can be applied for detection. The ARO exhibits a slow iteration speed exploration phase population prone an iterative stagnation condition exploitation phase, which hinders its ability deliver outstanding aforementioned problems. First, enhance global capabilities further, thinking incorporates mud ring feeding strategy from bottlenose dolphin optimizer (BDO). Simultaneously, adjusting phases, employs adaptive switching mechanism. Second, avoid original algorithm getting trapped local optimum during levy flight adopted. Lastly, dynamic lens-imaging introduced variety facilitate escape optimum. Then, this paper proposes modified ARO, namely LBARO, hybrid that combines BDO model. LBARO first empirically evaluated comprehensively demonstrate superiority proposed algorithm, using 8 benchmark test functions 4 UCI datasets. Subsequently, integrated into process model classification experimental validation. This integration validated utilizing NSL-KDD, UNSW NB-15, InSDN datasets, respectively. Experimental results indicate based on successfully reduces characteristics while detection.</p>

Язык: Английский

Процитировано

6
Advances in Artificial Rabbits Optimization: A Comprehensive Review DOI

Ferzat Anka,

Nazim Agaoglu,

Sajjad Nematzadeh

и другие.

Archives of Computational Methods in Engineering, Год журнала: 2024, Номер unknown

Опубликована: Дек. 7, 2024

Язык: Английский

Процитировано

5
Enhancing optimal sizing of stand-alone hybrid systems with energy storage considering techno-economic criteria based on a modified artificial rabbits optimizer DOI
Abdelazim G. Hussien, Hoda Abd El-Sattar, Fatma A. Hashim

и другие.

Journal of Energy Storage, Год журнала: 2023, Номер 78, С. 109974 - 109974

Опубликована: Дек. 20, 2023

Язык: Английский

Процитировано

11
Modular reconfiguration of hybrid PV-TEG systems via artificial rabbit algorithm: Modelling, design and HIL validation DOI
Bo Yang, Yulin Li, Jianxiang Huang

и другие.

Applied Energy, Год журнала: 2023, Номер 351, С. 121868 - 121868

Опубликована: Сен. 7, 2023

Язык: Английский

Процитировано

10
The Flood Simulation of the Modified Muskingum Model with a Variable Exponent Based on the Artificial Rabbit Optimization Algorithm DOI Creative Commons
Min Li,

Zhirui Cui,

Tianyu Fan

и другие.

Water, Год журнала: 2024, Номер 16(2), С. 339 - 339

Опубликована: Янв. 19, 2024

In order to further improve the accuracy of flood routing, this article uses Variable Exponential Nonlinear Muskingum Model (VEP-NMM), combined with Artificial Rabbit Optimization (ARO) algorithm for parameter calibration, construct ARO-VEP-NMM routing model. Taking Wilson’s (1974) as an example, model calculation results were compared and analyzed constructed seven optimization algorithms. At same time, six measured floods in Zishui Basin selected applicability testing. The show that ARO exhibits stronger robustness search ability other algorithms can better solve problem use accurately reflects movement patterns floods. Nash coefficient Wilson section reached 0.9983, average during validation period was 0.9, verifying adaptability feasibility routing. research provide certain references a theoretical basis improving forecasting.

Язык: Английский

Процитировано

3
Towards trustworthy civil aviation hazards identification: An uncertainty-aware deep learning framework DOI

Zhaoguo Hou,

Huawei Wang,

Minglan Xiong

и другие.

Advanced Engineering Informatics, Год журнала: 2025, Номер 65, С. 103280 - 103280

Опубликована: Март 29, 2025

Язык: Английский

Процитировано

0