Cite this DOI

Lekha Sri, L. S. (2023). Hotel Reviews Analysis Using Machine Learning Algorithms and Text Mining Model. *Journal of Science & Technology*, *8*(12), 31–39. https://doi.org/10.46243/jst.2023.v8.i12.pp31-39

@article{lekhasri2023hotel,
  author    = {Lekha Sri, Lekha Sri},
  title     = {{Hotel Reviews Analysis Using Machine Learning Algorithms and Text Mining Model}},
  journal   = {Journal of Science \& Technology},
  year      = {2023},
  month     = {dec},
  volume    = {8},
  number    = {12},
  pages     = {31--39},
  publisher = {Longman Publishers},
  issn      = {2456-5660},
  doi       = {10.46243/jst.2023.v8.i12.pp31-39},
  url       = {https://doi.org/10.46243/jst.2023.v8.i12.pp31-39},
  language  = {en},
  abstract  = {that enhances products, services, and marketing strategies. However, amidst the genuine feedback, a shadow looms—the challenge of fake reviews. These deceptive evaluations can be produced through humangenerated means, where content creators are paid to craft authentic-appearing but fictitious reviews. Alternatively, automated processes driven by textgeneration algorithms have become increasingly prevalent. Technological advancements in natural language processing (NLP) and machine learning (ML) have facilitated the automation of fake reviews, creating them at scale and a fraction of the cost compared to their human-generated counterparts. The significance of addressing fake reviews is underscored by scholarly contributions such as Wu et al.’s conceptual framework, which outlines an agenda for investigating fake reviews. Their work 1,2,3B.Tech Student, Department of Emerging Technologies (Cyber Security) from Malla Reddy College of Engineering and Technology, Hyderabad, India. 4Assistant Professor, Department of Emerging Technologies (Cyber Security) from Malla Reddy College of Engineering and Technology, Hyderabad, India. DOI:https://doi.org/10.46243/jst.2023.v8.i12.pp31-39 20 Lekha Sri, Aman Kumar Piyush, Puli Vikram, D Kalpana: Hotel Reviews Analysis Using Machine Learning Algorithms and Text Mining Model sheds light on the antecedents, consequences, and interventions in understanding this phenomenon. However, a recurring challenge in this domain is the lack of high-quality datasets, limiting the scope of research. Wu et al. notably address this by compiling and summarizing existing fake review-related public datasets. Another notable contribution comes from Liu et al., who propose a method for detecting fake reviews based on product-associated review records. Their approach involves analyzing the characteristics of review data and employing an isolation forest algorithm to detect outlier reviews. This method presents a fresh perspective on outlier review detection, with their experiments demonstrating its effectiveness. In essence, the exploration of fake reviews is not just an academic pursuit but a crucial aspect of navigating the increasingly complex landscape of online opinions. Addressing this challenge is vital for maintaining the integrity of customer feedback and ensuring that businesses can trust and act upon the information provided by reviews, ultimately fostering a more transparent and trustworthy digital marketplace. relevant datasets is emphasized, with studies often validating models on real review datasets. Accuracy metrics such as recall, precision, and F1 score are standard in evaluating model performance. Some studies introduce unique perspectives, such as considering timing elements in reviews or exploring collusion relationships between reviewers. Deep learning techniques and transformer models are frequently integrated, showcasing an interest in advanced methodologies. Additionally, the focus on specific domains, such as hotel reviews or online opinions, tailors detection methods to the nuances of the data. Overall, researchers consistently acknowledge current gaps in the field and propose future directions for more robust outcomes, reflecting the ongoing evolution of fake review detection research. In conclusion, this literature review highlights the diverse methodologies employed in the pursuit of fake review detection. From feature extraction techniques, and text mining, to advanced machine learning algorithms and unique perspectives on timing and collusion relationships, these studies collectively contribute to the ongoing efforts to create robust systems capable of identifying and mitigating the impact of deceptive reviews in online platforms. they explore the collusion relationship between reviewers to build a reviewer group collusion model. Evaluations show that the review group method and reviewer group collusion models can effectively improve the precision by 4\%–7\% compared to the baselines in the fake reviews classification task especially when reviews are posted by professional review spammers. METHODOLOGY The research paper on fake review detection using machine learning algorithms involves a systematic approach to model development and training the model, evaluation, and validation. Dataset Collection and Selection: Identify or construct a comprehensive and diverse dataset of online reviews, specifically focusing on the domain of interest, such as hotel reviews. This dataset should include both genuine and fake reviews. Data Preprocessing in Machine Learning: Data preprocessing is a process of preparing the raw data and making it suitable for a machine learning model. It is the first and crucial step in creating a machinelearning model. Generally contains noises, missing values, and maybe in an unusable format which cannot be directly used for machine learning models. Data preproces}
}

TY  - JOUR
TI  - Hotel Reviews Analysis Using Machine Learning Algorithms and Text Mining Model
AU  - Lekha Sri, Lekha Sri
JO  - Journal of Science & Technology
PY  - 2023
DA  - 2023/12/12/
VL  - 8
IS  - 12
SP  - 31
EP  - 39
PB  - Longman Publishers
SN  - 2456-5660
LA  - en
AB  - that enhances products, services, and marketing strategies. However, amidst the genuine feedback, a shadow looms—the challenge of fake reviews. These deceptive evaluations can be produced through humangenerated means, where content creators are paid to craft authentic-appearing but fictitious reviews. Alternatively, automated processes driven by textgeneration algorithms have become increasingly prevalent. Technological advancements in natural language processing (NLP) and machine learning (ML) have facilitated the automation of fake reviews, creating them at scale and a fraction of the cost compared to their human-generated counterparts. The significance of addressing fake reviews is underscored by scholarly contributions such as Wu et al.’s conceptual framework, which outlines an agenda for investigating fake reviews. Their work 1,2,3B.Tech Student, Department of Emerging Technologies (Cyber Security) from Malla Reddy College of Engineering and Technology, Hyderabad, India. 4Assistant Professor, Department of Emerging Technologies (Cyber Security) from Malla Reddy College of Engineering and Technology, Hyderabad, India. DOI:https://doi.org/10.46243/jst.2023.v8.i12.pp31-39 20 Lekha Sri, Aman Kumar Piyush, Puli Vikram, D Kalpana: Hotel Reviews Analysis Using Machine Learning Algorithms and Text Mining Model sheds light on the antecedents, consequences, and interventions in understanding this phenomenon. However, a recurring challenge in this domain is the lack of high-quality datasets, limiting the scope of research. Wu et al. notably address this by compiling and summarizing existing fake review-related public datasets. Another notable contribution comes from Liu et al., who propose a method for detecting fake reviews based on product-associated review records. Their approach involves analyzing the characteristics of review data and employing an isolation forest algorithm to detect outlier reviews. This method presents a fresh perspective on outlier review detection, with their experiments demonstrating its effectiveness. In essence, the exploration of fake reviews is not just an academic pursuit but a crucial aspect of navigating the increasingly complex landscape of online opinions. Addressing this challenge is vital for maintaining the integrity of customer feedback and ensuring that businesses can trust and act upon the information provided by reviews, ultimately fostering a more transparent and trustworthy digital marketplace. relevant datasets is emphasized, with studies often validating models on real review datasets. Accuracy metrics such as recall, precision, and F1 score are standard in evaluating model performance. Some studies introduce unique perspectives, such as considering timing elements in reviews or exploring collusion relationships between reviewers. Deep learning techniques and transformer models are frequently integrated, showcasing an interest in advanced methodologies. Additionally, the focus on specific domains, such as hotel reviews or online opinions, tailors detection methods to the nuances of the data. Overall, researchers consistently acknowledge current gaps in the field and propose future directions for more robust outcomes, reflecting the ongoing evolution of fake review detection research. In conclusion, this literature review highlights the diverse methodologies employed in the pursuit of fake review detection. From feature extraction techniques, and text mining, to advanced machine learning algorithms and unique perspectives on timing and collusion relationships, these studies collectively contribute to the ongoing efforts to create robust systems capable of identifying and mitigating the impact of deceptive reviews in online platforms. they explore the collusion relationship between reviewers to build a reviewer group collusion model. Evaluations show that the review group method and reviewer group collusion models can effectively improve the precision by 4%–7% compared to the baselines in the fake reviews classification task especially when reviews are posted by professional review spammers. METHODOLOGY The research paper on fake review detection using machine learning algorithms involves a systematic approach to model development and training the model, evaluation, and validation. Dataset Collection and Selection: Identify or construct a comprehensive and diverse dataset of online reviews, specifically focusing on the domain of interest, such as hotel reviews. This dataset should include both genuine and fake reviews. Data Preprocessing in Machine Learning: Data preprocessing is a process of preparing the raw data and making it suitable for a machine learning model. It is the first and crucial step in creating a machinelearning model. Generally contains noises, missing values, and maybe in an unusable format which cannot be directly used for machine learning models. Data preproces
DO  - 10.46243/jst.2023.v8.i12.pp31-39
UR  - https://doi.org/10.46243/jst.2023.v8.i12.pp31-39
ER  -

{
    "type": "article-journal",
    "id": "10.46243/jst.2023.v8.i12.pp31-39",
    "DOI": "10.46243/jst.2023.v8.i12.pp31-39",
    "URL": "https://doi.org/10.46243/jst.2023.v8.i12.pp31-39",
    "title": "Hotel Reviews Analysis Using Machine Learning Algorithms and Text Mining Model",
    "source": "Smart Scholars DOI Registry",
    "container-title": "Journal of Science & Technology",
    "author": [
        {
            "family": "Lekha Sri",
            "given": "Lekha Sri"
        }
    ],
    "issued": {
        "date-parts": [
            [
                2023,
                12,
                12
            ]
        ]
    },
    "volume": "8",
    "issue": "12",
    "page": "31-39",
    "publisher": "Longman Publishers",
    "language": "en",
    "abstract": "that enhances products, services, and marketing strategies. However, amidst the genuine feedback, a shadow looms—the challenge of fake reviews. These deceptive evaluations can be produced through humangenerated means, where content creators are paid to craft authentic-appearing but fictitious reviews. Alternatively, automated processes driven by textgeneration algorithms have become increasingly prevalent. Technological advancements in natural language processing (NLP) and machine learning (ML) have facilitated the automation of fake reviews, creating them at scale and a fraction of the cost compared to their human-generated counterparts. The significance of addressing fake reviews is underscored by scholarly contributions such as Wu et al.’s conceptual framework, which outlines an agenda for investigating fake reviews. Their work 1,2,3B.Tech Student, Department of Emerging Technologies (Cyber Security) from Malla Reddy College of Engineering and Technology, Hyderabad, India. 4Assistant Professor, Department of Emerging Technologies (Cyber Security) from Malla Reddy College of Engineering and Technology, Hyderabad, India. DOI:https://doi.org/10.46243/jst.2023.v8.i12.pp31-39 20 Lekha Sri, Aman Kumar Piyush, Puli Vikram, D Kalpana: Hotel Reviews Analysis Using Machine Learning Algorithms and Text Mining Model sheds light on the antecedents, consequences, and interventions in understanding this phenomenon. However, a recurring challenge in this domain is the lack of high-quality datasets, limiting the scope of research. Wu et al. notably address this by compiling and summarizing existing fake review-related public datasets. Another notable contribution comes from Liu et al., who propose a method for detecting fake reviews based on product-associated review records. Their approach involves analyzing the characteristics of review data and employing an isolation forest algorithm to detect outlier reviews. This method presents a fresh perspective on outlier review detection, with their experiments demonstrating its effectiveness. In essence, the exploration of fake reviews is not just an academic pursuit but a crucial aspect of navigating the increasingly complex landscape of online opinions. Addressing this challenge is vital for maintaining the integrity of customer feedback and ensuring that businesses can trust and act upon the information provided by reviews, ultimately fostering a more transparent and trustworthy digital marketplace. relevant datasets is emphasized, with studies often validating models on real review datasets. Accuracy metrics such as recall, precision, and F1 score are standard in evaluating model performance. Some studies introduce unique perspectives, such as considering timing elements in reviews or exploring collusion relationships between reviewers. Deep learning techniques and transformer models are frequently integrated, showcasing an interest in advanced methodologies. Additionally, the focus on specific domains, such as hotel reviews or online opinions, tailors detection methods to the nuances of the data. Overall, researchers consistently acknowledge current gaps in the field and propose future directions for more robust outcomes, reflecting the ongoing evolution of fake review detection research. In conclusion, this literature review highlights the diverse methodologies employed in the pursuit of fake review detection. From feature extraction techniques, and text mining, to advanced machine learning algorithms and unique perspectives on timing and collusion relationships, these studies collectively contribute to the ongoing efforts to create robust systems capable of identifying and mitigating the impact of deceptive reviews in online platforms. they explore the collusion relationship between reviewers to build a reviewer group collusion model. Evaluations show that the review group method and reviewer group collusion models can effectively improve the precision by 4%–7% compared to the baselines in the fake reviews classification task especially when reviews are posted by professional review spammers. METHODOLOGY The research paper on fake review detection using machine learning algorithms involves a systematic approach to model development and training the model, evaluation, and validation. Dataset Collection and Selection: Identify or construct a comprehensive and diverse dataset of online reviews, specifically focusing on the domain of interest, such as hotel reviews. This dataset should include both genuine and fake reviews. Data Preprocessing in Machine Learning: Data preprocessing is a process of preparing the raw data and making it suitable for a machine learning model. It is the first and crucial step in creating a machinelearning model. Generally contains noises, missing values, and maybe in an unusable format which cannot be directly used for machine learning models. Data preproces",
    "ISSN": "2456-5660"
}

From the record as registered (version 2) — the record and its history. Programs: https://registry.smartscholars.in/api.php?action=cite&doi=10.46243%2Fjst.2023.v8.i12.pp31-39 gives all four in one JSON answer.