Natural language processing for analyzing online customer reviews: a survey, taxonomy, and open research challenges

Sentiment analysis and opinion mining

Sentiment analysis involves extracting and classifying opinions, emotions, and attitudes expressed in textual data to determine whether a text expresses a positive, negative, or neutral sentiment. In contrast, opinion mining, also known as subjectivity analysis, focuses on identifying and analyzing subjective information from various sources, such as reviews, social media, and discussions. Many studies have examined deep neural networks and traditional algorithms for sentiment extraction in multiple domains. A study used Bing Liu’s aspect-based opinion-mining approach to tourism, addressing specific elements absent from the physical product model. The authors detected elements in online travel reviews and proposed advanced NLP-based sentiment categorization methods. They used a general tool architecture for Lake District TripAdvisor reviews and increased the performance, reaching a 92% F-measure for the sentiment classification (Marrese-Taylor, Velásquez & Bravo-Marquez, 2014). A study categorized sentiments and varied emotions from a large dataset of internet mobile phone reviews using sentiment analysis. This comprehensive strategy helped consumers and producers make informed decisions by emphasizing the relevance of online reviews in determining client needs and providing timely feedback (Singla, Randhawa & Jain, 2017).

A study also used cognitive computing-based Artificial Intelligence (AI) technologies to examine textual content and numerical ratings in online reviews. The study examined hotel reviews using sentiment analysis to uncover discrepancies between review content and scores (Fazzolari et al., 2017). Additionally, a study developed a Chinese sentiment mining method that outperformed other models on TripAdvisor reviews and included features to improve sentiment analysis (Li & Yang, 2017). A study also used Amazon and Twitter data to develop an NLP and machine learning book review sentiment categorization system. Users might analyze public opinion and create user-friendly word clouds based on top attributes (Magesh & Swarnalatha, 2017). Genetic Algorithms for automated text sentiment analysis performed well on huge Amazon datasets and were highlighted for business and scientific applications (Dufourq & Bassett, 2017).

Deep learning has been utilized in sentiment extraction using convolutional neural network (CNN) and long short term memory (LSTM) architectures to extract features from customer reviews (Jain, Kumar & Mahanti, 2018). Another study examined the role of opinion mining in e-commerce, using algorithms such as naïve Bayes, Support Vector Machine (SVM), random forest, and hybrid SVM to classify reviews as positive or negative, improving understanding and the use of opinion mining in online reviews (Gawade & Parthiban, 2018). NLP was also used for Amazon reviews to enhance service by comparing K-nearest neighbour, SVM, and decision tree classification algorithms to analyze customer feedback (Aryo Prakoso et al., 2018). Deep learning techniques like word2vec for word embedding and CNN were used to evaluate social marketing tactics and help consumers make informed purchase decisions (Panthati et al., 2018). Another study used classical machine learning and deep learning to classify multiple affective attributes with over 90% accuracy using customer emotional needs from online product reviews (Wang et al., 2018). A study modified the Opinion Mining system evaluation by using a user profiling system to parameterize the system based on user preferences and improve results (Angioni et al., 2018).

A study examined opinion mining and sentiment analysis of Amazon product reviews to increase accuracy. The proposed Senti algorithm outperformed sentiment analysis APIs, allowing for improved commercial, political, and financial decision-making (Karthikayini & Srinath, 2018). Another research used Hybrid Attribute Based Sentiment Classification (HABSC) to identify sentiment orientation in online consumer reviews. HABSC outperformed state-of-the-art approaches by integrating syntactic characteristics, implicit word relations, and domain-specific information to reveal differences in review content and ratings between local and international consumers on multinational social commerce platforms (Bansal & Srivastava, 2019). Japanese restaurant reviews were also examined to see how ethnic culture affects customer ratings. Bilingual text mining technique highlighted cultural implications in social commerce by showing different emotion distribution patterns among Japanese and Western customers (Nakayama & Wan, 2019).

Researchers also examined sentiment analysis in NLP to evaluate emerging technologies with many aspects. Mobile reviews were identified using web scraping and machine learning techniques, specifically decision tree and SVM, with over 90% accuracy using 1–2 grams. User experience and marketing tactics improved by real-time product review sentiment analysis (Chauhan & Sehgal, 2019). A study examined the importance of sentiment analysis in business analytics for product and market competitiveness. The research examined machine learning classification methods, including a hybrid algorithm, emphasizing the rising relevance of sentiment analysis in corporate strategy and product quality (Jabbar et al., 2019; Pathuri et al., 2019). A study addressed the constraints of using customer ratings or review summaries to extract valuable data from online product reviews (Dharaiya et al., 2020). Two new corpora with full word clouds were produced using a general approach and a specific approach to improve product analysis accuracy and efficiency. The approach examined varied consumer sentiment and product characteristics. Additionally, a new sentiment analysis algorithm improved the Dempster-Shafer algorithm (Jamadi Khiabani, Basiri & Rastegari, 2020). This novel method treated reviews as sentences with sentiment orientations and ratings. The method outperformed the original algorithm on TripAdvisor and CitySearch datasets.

Lexicon-based analysis was used to evaluate Amazon books and writers (Khatun et al., 2020). The study used a bag-of-words technique to evaluate review positivity and negativity, emphasizing the importance of sentiment in market analysis and its ability to anticipate business trends. Another study compared LSTM, random forest, SVM, and eXtreme Gradient Boosting (XGBoost) for sentiment analysis (Chatterjee et al., 2021a). The findings highlighted applications in customer management systems and Twitter and e-commerce platforms. Two aspect-based sentiment analysis extraction algorithms were presented to analyze unstructured social media reviews (Bhamare & Prabhu, 2021). Using SemEval, Yelp, and Kaggle datasets, the hybrid technique predicted aspect categories accurately. An end-to-end sentiment analysis technique for negotiations was introduced by Mukherjee et al. (2021). The method reduced biases and enhanced sentiment categorization across datasets. Sentiment analysis improved user experience on e-commerce platforms(Gupta, Rastogi & Katal, 2021). Compared to logistic regression, multinomial naïve Bayes, and SVM, stochastic gradient descent has the highest accuracy. A lexicon-based technique and logistic regression were used to analyze Web sentiment (Khanam & Sharma, 2021). These methods successfully extracted sentiments from various web sources.

A unique Statistics-Based Outlier Detection and Correction Method study (Chatterjee et al., 2021b) highlighted the need for proper sentiment analysis in Amazon customer reviews. This technique improved sentiment analysis without data loss over previous systems. Sentiment analysis was performed on Amazon electronics product reviews using different machine learning algorithms (Urkude et al., 2021). Logistic regression had the best accuracy, demonstrating the relevance of sentiment analysis in customer recommendations. Another work used part-of-speech-based feature extraction and game-theoretic rough sets to reduce dimensionality in sentiment analysis (Chen & Yao, 2021). The model outperformed other models and classifiers. A study on Amazon Electronics product reviews using machine learning due to the rising relevance of e-commerce (Hawlader et al., 2021). Preprocessing methods were tested, and the multi-layer perceptron classifier performed well. A publication introduced the BERT Base Uncased model to improve e-commerce platform review sentiment analysis, outperforming standard machine learning approaches (Geetha & Karthika Renuka, 2021). A work using NLP for sentiment analysis addressed Amazon’s growing customer review volume (Sinnasamy & Sjaif, 2022). The Term Frequency–Inverse Document Frequency (TF-IDF) approach using unigram and SVM was the most accurate for Amazon product reviews.

An Ensemble Classifier study (Maurya & Pratap, 2022) stressed the importance of online reviews in understanding customer perspectives and needs. The Ensemble Classifier outperformed machine learning techniques in consumer feedback analysis. A article used naïve Bayes, random forest, and SVM algorithms to improve the accuracy of sentiment analysis for Amazon product reviews (Naureen, Siddiqa & Devi, 2022). Aspect-based BERT models were used for tourist sentiment analysis (Chu et al., 2022). The findings helped vendors improve their products and services and provided users with personalized recommendations. A mixed generative-discriminative strategy combining Fisher kernels and hidden Markov models improved textual sentiment analysis (Nasfi & Bouguila, 2022). Amazon and IMDb user reviews showed that the method improved sentiment identification compared to existing techniques. The influence of digitalization on e-commerce and information overload was examined using machine learning algorithms on Amazon fine food reviews (Yarkareddy, Sasikala & Santhanalakshmi, 2022). The authors attempted to simplify review analysis so customers could quickly and accurately assess product opinions. Another research examined BERT-based sentiment analysis across domains (Roccabruna, Azzolin & Riccardi, 2022). The study showed that sentiment analysis should incorporate class label variations from various sources.

A study used a hybrid method for sentiment analysis of Amazon customer reviews using NLP, machine learning, and deep learning (Juyal, 2022). A study demonstrated that analyzing sentiment can enhance brand value, advertising, and customer service. SVM and CNN models were used to perform sentiment analysis on an e-commerce platform by Uma et al. (2022). Both methods were found to be more accurate compared to others. A study investigated the effectiveness of using machine learning for review sentiment analysis (Kamalesh & Vijayalakshmi, 2022). A study also attempted to utilize NLP to automate the analysis of product reviews from various platforms, such as Amazon (Singh et al., 2022). The approach used machine learning to train a neural network to classify product reviews as positive, neutral, or negative. A study examined how varied NLP algorithms affected Yelp and Zappos data (Yang, Pang & Kan, 2022). Neural networks and BERT offered insights into algorithm selection that were useful for consumer review analysis. The research used NLP methods like TF-IDF Vectorizer and Count Vectorizer to create a food industry model. Logistic regression, dummy classifier, and random forest classifier were used to efficiently analyze online review sentiments, giving manufacturers significant product perception insights. The investigation found that the proposed sentiment analysis model worked (Gupta et al., 2022). Another article proposed a Bayesian network architecture for sentence-level sentiment analysis of e-commerce product reviews with automated rule creation and progressive retainability. The study met model requirements instantaneously, demonstrating its scalability and durability in opinion mining across various domains (Hariharan et al., 2023).

A new method using agglomerative clustering for outlier detection and a stacked autoencoder with ensemble classification algorithms was developed to detect sarcastic tweets and reviews. This technique outperformed other algorithms in sarcasm prediction and sentiment identification with 99.3% accuracy (Maheswari & Dhenakaran, 2023). With 1.5 million Amazon and Yelp reviews, a study introduced the ‘Amazon and Yelp Reviews’ dataset for sentiment analysis. The sentiment analysis approach achieved 87.3% accuracy by utilizing a Bidirectional LSTM (BiLSTM) model, user comment preparation, and daily data collection. The dataset and methodology can be used for consumer feedback analysis and online reputation management (Geetha et al., 2023). Amazon values customer opinions and stresses the importance of customer satisfaction in organizational success. The article used NLP to turn text into numerical arrays for machine learning techniques. Five scores were assigned to Amazon reviews using supervised machine learning algorithms, such as SVM, naïve Bayes, and decision tree (Dharrao et al., 2023). Another article used machine learning to assess Amazon product review sentiment across categories. Text Blob, logistic regression, SVM, and multinomial naïve Bayes improved sentiment classification accuracy, proving that various review sentiment ratings can be predicted (Kumar, 2023). A study (Mehul et al., 2023) focused on sentiment polarity analysis for e-commerce customer reviews, while (Solairaj, Sugitha & Kavitha, 2023) presented an EESNN-SA-OPR method utilizing Collaborative Filtering (CF) and product-to-product similarity.

A study investigated business strategies for customer retention and attraction, employing an NLP-based sentiment analysis (Sumathi & Santharam, 2023). The impact of internet reviews on consumer decisions was examined using a CNN model for text review sentiment classification. Comparative analysis showed that the CNN model achieved 90% accuracy using Amazon reviews. Stop words are crucial to sentiment analysis, and the CNN model outperforms other algorithms on big datasets (Qorich & El Ouazzani, 2023). A publication also introduced the Adaptive Particle Grey Wolf Optimizer with Deep Learning Based Sentiment Analysis (APGWO-DLSA) approach for sentiment analysis on online product reviews using NLP and machine learning algorithms. The proposed technique on the Cell Phones And Accessories (CPAA) dataset performed better, obtaining 94.77% accuracy (Elangovan & Subedha, 2023). NLP and LSTM were used to create a customer review summary model to handle the increase in textual data. The hybrid sentiment analysis method provided organizations with important insights due to its excellent accuracy (94.46%), recall (91.63%), and F1-score (92.81%) (Kaur & Sharma, 2023).

A study on mobile phone reviews utilized consumer reviews to improve post-purchase products. After testing SVM, naïve Bayes, and logistic regression algorithms, the Random Forest (Unigram) classifier performed best on a balanced dataset, highlighting the importance of sentiment analysis in consumer feedback for product development (Venkataraman & Jadhav, 2023). LSTM and naïve Bayes were compared for sentiment analysis of online product reviews. Comprehensive assessments of varied internet items were conducted to understand user attitudes better (Meghana et al., 2023). A recent article uses data mining to analyze sentiments on Facebook, Instagram, Twitter, and Amazon. The research used consumer input to improve corporate strategy and predict customer requirements. Twitter data obtained via the Twitter API was analyzed using NLP techniques, demonstrating their ability to provide organizations with essential insights for personalized marketing and organizational benefit (Kshirsagar et al., 2023). The summary of existing literature on sentiment analysis and opinion mining is given in Table S2.

Review analysis and management

Review analysis and management include studies on analyzing online customer reviews to ensure their authenticity, trustworthiness, quality, and usefulness in e-commerce. Initiatives have been taken to address fake reviews and counterfeit goods in the context of online marketplaces. AI methods like NLP and topic analysis were used to detect counterfeit items on Amazon and eBay. Topic analysis of product and seller reviews identified deception-related keywords and concepts. The findings showed that automated counterfeit detection might boost online marketplace trust and efficiency (Wimmer & Yoon, 2015). The fake Product Review Monitoring and Removal System (FaRMS) analyzed reviews from numerous platforms with 87% accuracy in English and Unique Urdu support to combat fake reviews. By providing honest product ratings, FaRMS sought to improve customer satisfaction (Ata Ur et al., 2019).

A study examined how review length affects online purchasing decisions and questioned the idea that lengthier reviews are always better. Using Amazon reviews and advanced NLP, the study discovered that argumentation frequency altered the association between review length and helpfulness, showing that longer reviews were not always more helpful (Lutz, Pröllochs & Neumann, 2019). A novel approach combined business data and user reviews to improve relevance and diversity in machine-generated fake reviews. The proposed model generated high-quality and diverse reviews in response to seller descriptions (Jin, Zhang & Zhang, 2019). The significance of vigilance when dealing with manipulation on large online platforms was highlighted by stylometry-based algorithms that detected misleading online reviews (Sadman et al., 2020).

A predictive model used BERT and deep learning to improve online product review usefulness evaluation and overcome previous model limitations (Xu, Barbosa & Hong, 2020). Introducing Social Network Strength (SNS) elements to analyze the influence of friends and followers on review helpfulness enabled overcoming information overload in online customer reviews. The methodology evaluated using Yelp business reviews gave insights to researchers, businesses, reviewers, and review platforms (Bilal et al., 2021). In order to combat the ubiquity of fake reviews, supervised machine learning was utilized to identify opinion spammers, which improved the accuracy of spotting fraudulent reviews on well-known platforms (Jain, Pamula, Ansari 2021).

Addressing the critical issue of fake review detection, NLP techniques and machine learning models, including Naïve Bayes and random forest, were applied to combat the increasing prevalence of fake reviews in the E-commerce industry. The models demonstrated scalability, offering a solution for platforms to identify and address spam reviews promptly (Anas & Kumari, 2021). Another study aimed to determine the most effective feature combination for detecting fake reviews, highlighting the significance of behavior-related features in combination with text-related features, with verified purchases emerging as a crucial factor (Birim et al., 2022). A hybrid CNN-LSTM deep learning model with sentiment analysis techniques was employed to assess the authenticity of customer reviews, proposing a solution to combat fraudulent reviews in the e-commerce sector (Aishwarya & Prashanth Kumar, 2023).

Supervised machine learning and NLP techniques were utilized to identify and remove fake reviews from a dataset, focusing on significant E-commerce platforms to combat the prevalence of counterfeit product reviews impacting customer decisions and profits (Thilagavathy et al., 2023). A Python-based system was introduced to detect fake product reviews on Amazon, using SVM techniques to distinguish between genuine and fake reviews and enhance the reliability of product reviews (Iliev et al., 2023). Lastly, an innovative method employing a CNN and adaptive particle swarm optimization with NLP techniques achieved a remarkable 99.4% accuracy in identifying fake online reviews, offering practical implications for consumers, manufacturers, and sellers in maintaining the trustworthiness of online reviews (Deshai & Bhaskara Rao, 2023). Another study proposed a generalized solution by fine-tuning the BERT model to predict review helpfulness, demonstrating better performance compared to traditional bag-of-words methods (Bilal & Almazroi, 2023). The summary of existing literature on review analysis and management is given in Table S3.

Customer experience and satisfaction

The term customer experience includes all customer interactions with a company, from browsing online to receiving support after purchase. These interactions eventually affect the customer’s perception and loyalty towards the company. On the other hand, satisfaction refers to the degree of contentment that a customer feels with the products or services received. This can often be determined through customer feedback, reviews, and ratings. A study adopted Bing Liu’s aspect-based technique to identify customer preferences in TripAdvisor hotel and restaurant reviews to examine opinion mining in tourism. The approach demonstrated 90% precision and recall in extracting sentiment orientations, though it struggled with explicit aspect expressions. Emphasizing the value of tourism product reviews, the research underscored the importance of aspect-based opinion mining in revealing customer preferences (Marrese-Taylor et al., 2013). Another study focused on English online reviews of hotels, employing NLP and sentiment analysis. Organizations emphasizing these techniques outperformed peers in growth, earnings, and performance metrics, offering practical implications for hotel managers to leverage social media reviews for strategic decision-making (Tian et al., 2016).

Introducing a novel method for hotel summaries from travel forums, a study incorporated author credibility and conflicting opinions. Using a new sentence importance metric and k-medoids clustering algorithm, the approach outperformed conventional methods, confirmed by subjects for providing more comprehensive hotel information (Hu, Chen & Chou, 2017). In retail, an article proposed an online platform using NLP to analyze customer sentiments and streamline input through speech-to-text technology. The focus was on enhancing the shopping experience by understanding emotions expressed in reviews and suggesting smart shop solutions to improve overall customer satisfaction (Rogojanu et al., 2018). Another research attempted to create artificial personal shoppers for e-commerce platforms, emphasizing user engagement and trust. The study adapted existing information retrieval and NLP technologies to establish the groundwork for effective voice-based artificial personal shoppers in the online shopping domain (Limsopatham, Rokhlenko & Carmel, 2018).

A unique approach assessed customer loyalty through sentiment analysis of online reviews, achieving a 94% accuracy in determining loyalty types. Leveraging tokenization, lemmatization, and SentiWordNet, the study utilized a fuzzy logic model with rule-based systems, surpassing previous methods (Ghani, Bajwa & Ashfaq, 2018). Another study used NLP to extract insights from user-generated product reviews to address the need for general e-commerce platforms for vitamins and nutraceuticals. The system provided a five-point rating system, summarized commonly discussed topics, and offered representative reviews, empowering consumers with tailored information for informed decisions (John et al., 2019). A study proposed a rapid customer loyalty model for e-commerce with a 72% loyalty rate from Amazon.com reviews (Ashfaq & Kausar, 2019). Similarly, sentiment analysis and opinion mining in Yelp datasets using aspect-based sentiment analysis provided business strategies based on 1-year forecasted data, emphasizing the importance of leveraging online reviews to improve customer satisfaction (Ching & De Dios Bulos, 2019).

Analyzing user-generated hotel review data comprehensively, a study employed various techniques, achieving high precision (0.95) and recall (0.96). Visual analytics revealed patterns in user ratings, emphasizing the potential for improving business services and product quality (Chang, Ku & Chen, 2019). Investigating the impact of latent content factors on online review helpfulness, the study found that argument quality and valence significantly influenced review helpfulness. This approach surpassed previous manifest content and reviewer-related factors, enhancing understanding and addressing sentiments for improved customer satisfaction (Srivastava & Kalro, 2019). A study reviewed online reviews of hotel guest experiences and distinguished patterns between Asian and non-Asian guests, revealing service failures in different domains and stages of the hotel guest cycle (Sann & Lai, 2020).

Leveraging logistic regression and NLP, another study identified sentiment and topics among tourists in Cyprus, offering insights into the complex relationship between tourist culture, purchasing power, and reviews (Christodoulou, Gregoriades & Papapanayides, 2020). A study addressed the problem of processing user feedback quickly and effectively by introducing a crowdsourcing technique for categorizing app store reviews, suggesting that crowdsourcing has the potential to be a reliable and low-cost source for classifying user reviews (van Vliet et al., 2020). Investigating parental preferences for childcare using Yelp reviews revealed variations in satisfaction based on income levels, emphasizing safety, learning environment quality, and child-teacher interactions as pivotal factors (Herbst et al., 2020). Exploring opinion summarization in Web 3.0 platforms, a study proposed a novel graph-based abstractive technique, comparing it with extractive methods for coherence and completeness in generating summaries (Bhatia, 2021).

Enhancing review-based question-answering systems using NLP models, a study addressed the challenge of manual handling of product-related queries on online platforms. The proposed enhancements, including BERT, significantly improved response effectiveness, achieving a BLEU score of 0.58 (Moharkar et al., 2022). Analyzing visitor reviews of Croatia’s Plitvice Lakes National Park, a study utilized multidimensional scaling, sentiment analysis, and NLP to identify key topics and analyze strengths and weaknesses, providing valuable insights for protected natural areas (Sergiacomi et al., 2022). A study identified critical elements influencing success through text mining and sentiment analysis on TripAdvisor reviews, highlighting the significance of tour guides in consumer satisfaction (Barbierato, Bernetti & Capecchi, 2022). Furthermore, a study introduced a hierarchical attention network-based framework for analyzing Amazon Smartphone reviews (Ratmele & Thakur, 2022).

A study used sentiment analysis to classify smartphone reviews and predict product ratings based on user feedback (Suresh & Gurumoorthy, 2022). Addressing information overload in Community-based Question Answering (CQA) platforms, a study introduced a CQA summarization task. Evaluating various summarization methods, the research provided a robust baseline for CQA summarization, contributing to the user experience in navigating overwhelming information (Hsu, Suhara & Wang, 2022). Assessing pre-trained transformers for sentiment extraction, a study applied five models to an Amazon database of automotive products, suggesting their potential for practical applications like product monitoring and market research (Alves, Lobo & Reis, 2022). Lastly, employing machine learning and NLP, a study demonstrated the effectiveness of text summarization in efficiently handling and comprehending extensive online product review data (Nainwal et al., 2023). The summary of existing literature on customer feedback and satisfaction is given in Table S4.

User profiling and recommendation systems

User profiling and recommendation systems aim to improve personalized user experiences across different platforms. Two innovative algorithms were introduced to address challenges related to service recommendation accuracy and incomplete modalities in recommender systems. Value Features and Distributions for Accurate Service Recommendation (VFDSR) leverages fine-grained value features extracted from customer reviews to enhance personalized service recommendations, demonstrating better performance on a Yelp dataset (Wang et al., 2017). Learning to recommend with missing modalities (LRMM) tackles incomplete modalities through modality dropout and a multimodal sequential autoencoder, outperforming existing methods and proving robust in mitigating data sparsity and the cold-start problem (Wang, Niepert & Li, 2018). Integrating data mining, human psychology, and NLP aimed to enhance recommender-based mobile applications. The strategy generated “wh” questions from recommended items, utilizing a web scraper for relevant information, and strategically employed human-computer interaction psychology to increase user engagement. Survey results confirmed an improved hit rate, supporting the method’s effectiveness on platforms like Amazon (Neeraj, Oswald & Sivaselvan, 2018).

Another study focused on the rising use of intelligent personal assistants in business workflows, introducing an explanation mode feature for speech interaction in Enterprise Resource Planning software. Task attraction was identified as pivotal for usefulness, emphasizing the supplementary role of intelligent personal assistants alongside traditional input methods (Hüsson, Holland & Sánchez, 2020). Advancements in personalized advertising and recommender systems were explored with Double Attention for Click-Through Rate Prediction (DAMIN), an enhanced model incorporating a double attention mechanism into the Deep Interest Network. Experimental results on Amazon datasets demonstrated DAMIN’s effectiveness, improving AUC by 4–5% compared to classical models (Xia, Fang & Shi, 2021). TripAdvisor data was leveraged to enhance hotel customer targeting through a fine-tuned BERT model and a multi-criteria recommender system. Outperforming a benchmark single-criteria system, the approach considered varied hotel aspects, demonstrating better performance (Zhuang & Kim, 2021). In the Pakistani fashion industry, user interests were extracted from social media using Latent Dirichlet Allocation (LDA), Latent Semantic Analysis (LSA), and BERT for topic modeling, sentiment analysis tools, and K-Means for clustering. Empirical validation demonstrated moderate agreement between human and machine evaluations (Tahir & Asif Naeem, 2022).

An innovative product recommender model for e-commerce platforms analyzed customer reviews using NLP, sentiment analysis, and clustering algorithms. Experiments on Amazon datasets showed notable enhancement in multi-node cluster setups over single-node configurations (Patidar & Patel, 2022). A graph-based movie recommender system incorporating user sentiments and emotions demonstrated better performance. Utilizing BERT for sentiment analysis and a Kaggle dataset, the proposed IGMC-based models outperformed conventional and state-of-the-art graph-based systems (Lee et al., 2022). The impact of cognitive absorption dimensions on continuous use intention in AI-driven Recommender Systems was investigated, revealing that curiosity and focused immersion significantly influenced continuous use intention (Acharya, Sassenberg & Soar, 2024).

The study proposed a novel approach to enhance tourist trip suggestions by integrating neural networks and deep learning techniques. The hybrid framework combined Neural Network-LSTM for Point of Interest recommendations and BERT for sequential trip recommendations, demonstrating better performance on TripAdvisor and Yelp datasets (Noorian, Harounabadi & Hazratifard, 2023). A weighted hybrid recommendation method combining user reviews, rating data, and sentiment analysis improved precision scores on the Amazon Reviews dataset, integrating CF for enhanced recommendations (Paul & Singh, 2023). FusionSCF addressed issues in Recommendation Systems by integrating CF with sentiment analysis of textual user reviews. Using e-commerce datasets, the model combined weighted ratings and sentiment scores to enhance recommendations, demonstrating the effectiveness of the sentiment-based model over traditional CF methods. The study also explored the impact of fake reviews on the filtering system (Ananth, Raghuveer & Vasanth Kumar, 2023). The summary of existing literature on user profiling and recommendation systems is given in Table S5.

Marketing and brand management

Marketing involves promoting and selling products or services to target audiences, whereas brand management involves managing a brand’s reputation, perception, and value in the marketplace. Advanced methods for opinion mining in concise e-commerce feedback were studied by a study to create seller rating profiles. The novel approaches integrated opinion mining and dependency relation analysis to propose an algorithm for extracting dimension ratings. The computation of dimension weights from ratings was framed as a factor analytic problem and solved through matrix factorization. The algorithm demonstrated its effectiveness on eBay and Amazon datasets, achieving 93.1% and 89.64% accuracy in identifying dimensions and ratings, respectively (Cui et al., 2013). CommTrust, a novel approach to the ‘all good reputation’ problem in e-commerce trust models, leveraged free-text feedback comments to create a multidimensional trust model. The algorithm, combining NLP, opinion mining, and topic modeling, effectively mitigated universally high seller reputation scores on eBay and Amazon, providing a more reliable ranking of sellers based on trust (Zhang, Cui & Wang, 2014).

Another study combined opinion mining and CF algorithms to analyze Yelp data, highlighting inconsistencies between textual reviews and star ratings. The research explored the impact of restaurant popularity on user ratings, yielding improved results with a lower root mean squared error (RMSE) (Angioni, Clemente & Tuveri, 2015). The significance of consumer reviews in e-commerce was emphasized in a distinct model that focused on fine-grained analysis of feedback. The methodology, validated on Amazon and Flipkart, revealed notable discrepancies in trust scores, enhancing the understanding of seller trust profiles (Bhargava et al., 2016). The impact of Amazon’s Verified Purchase badge on review helpfulness and product ratings was investigated, revealing significant increases in review helpfulness and product ratings for verified purchase reviews (Kokkodis & Lappas, 2016).

A study used various relevance algorithms to enhance Amazon Search’s relevance ranking, emphasizing the significant impact on customer satisfaction and financial outcomes (Sorokina & Cantú-Paz, 2016). Different methods for analyzing consumer opinions on platforms like Amazon were explored, introducing a hybrid approach that effectively ranked products based on text reviews, question answer (QA) data, and star ratings, enhancing sales predictions (Anjum & Sabharwal, 2016). The study addressed the financial and reputational impact of product issues in Over-the-Counter (OTC) pain relief products, utilizing Amazon’s product reviews to identify safety and efficacy concerns through “smoke word” dictionaries and sentiment analysis (Adams, Gruss & Abrahams, 2017). Another research investigated whether models trained on a dataset could accurately reflect human proficiency in online review writing, employing knowledge tracing to track the development of reviewers’ skills over time (Megasari et al., 2018).

The challenge of navigating through lengthy customer reviews was addressed through a multi-criteria decision-making approach to recommend optimal products on platforms like Flipkart and Amazon (Kumar, 2018). The detection of ironic opinions in social networks and e-commerce was explored, and feature-based irony detection was compared with a novel approach using character language model classifiers, showing competitive accuracy in experiments (Clavel Quintero & Arco García, 2018). The evolving landscape of consumer behavior in e-commerce was examined, and an algorithmic solution was proposed to mitigate inaccuracies in user-generated reviews and enhance the decision-making process using NLP techniques (Mastan Rao et al., 2018). The Ranking Hotels using Aspect Level Sentiment Analysis (RHALSA) algorithm was introduced, effectively evaluating and ranking hotels based on user reviews through aspect-level sentiment analysis on a Tripadvisor dataset (Panigrahi & Asha, 2018).

Leveraging user-generated content for marketing was explored through sentiment analysis tools, proposing a framework to derive new scores reflecting consumer sentiments for distinct product features on Amazon (Kauffmann et al., 2019). The impact of technology on people’s lifestyles and decision-making processes was investigated using Yelp, emphasizing the importance of reviews analysis in monitoring changes in business public opinion over time (Galli et al., 2019). A Feature-Based Product (FBP) Recommendation system using NLP and sentiment analysis on Amazon mobile product reviews was proposed, demonstrating the effectiveness of SVM in suggesting the best company products for user-requested features (Koneru et al., 2019). The Level of Success model (LOS) was introduced, employing NLP, review quantification, and image analysis to contribute valuable insights for effective product market evaluation in the Amazon online market review context (Li et al., 2020).

Quantifying online brand image (OBIM) by analyzing consumer reviews was explored, introducing a model that evaluated associations’ favorability, strength, and uniqueness through sentiment and co-word network analysis (Mitra & Jenamani, 2020). Using Python for preprocessing NLP features, the study focused on product recommendations on Amazon, revealing insights for quarterly sales forecasting and product development trends based on customer reviews (Yang et al., 2020). A novel method, Tagging Product Review (TPR), was introduced to summarize e-commerce product reviews, achieving high tag relevance scores for both popular and cold products on Amazon (Konjengbam, Kumar & Singh, 2020). AmazonRep, a reputation system that considers review sentiment, helpfulness votes, review timing, and user credibility, proved effective in generating and presenting reputations for diverse products on Amazon (Benlahbib & Nfaoui, 2020b). Reputation generation for diverse entities using customer reviews was addressed through a unified reputation value integrating helpfulness, time, rating, and sentiment. The method outperformed three existing systems, offering a comprehensive approach and visualizations for numerical reputation, opinion categories, and top reviews (Benlahbib & Nfaoui, 2020a).

A study validated sustainable features for French Press coffee carafes extracted from Amazon reviews using a novel design technique called collage placement. The study revealed a disparity between customer perceptions and engineered sustainability, emphasizing the importance of understanding diverse perspectives. Participants evaluated products based on social, environmental, and economic sustainability, highlighting the efficacy of the collage method in assessing sustainability perceptions. Demographic variations in sustainability perceptions further underscored the method’s relevance (El-Dehaibi, Liao & MacDonald, 2021). Another research focused on online sales strategies for Amazon products, using sentiment analysis and opinion mining for microwave ovens, baby pacifiers, and hairdryers. Mathematical models evaluated product reputation trends, predicting potential success or failure and proposing design features for enhanced desirability (Liu, 2021).

The study on online product reviews from Flipkart and Amazon employed sentiment analysis and a bag-of-words model to assess the impact on third-party sellers. Categorizing reviews and conducting topic modeling, the findings emphasized the importance of considering both product and seller reviews for a seamless delivery and defect-free product that benefits both buyers and sellers (Nellutla et al., 2021). Introducing a novel approach for computing reputation scores, the article utilized a BiLSTM, recurrent neural network (RNN), and NLP techniques to analyze textual opinions on online platforms like IMDB and Amazon. Experimental results demonstrated the method’s effectiveness, aligning closely with ground truth and suggesting practical applicability for reputation generation (Boumhidi, Benlahbib & Nfaoui, 2021).

A study on TripAdvisor reviews and online weather data used NLP to assess the impact of weather conditions on tourists’ intention to revisit a destination. Enriching the dataset with weather information and hotel ratings, the findings identified factors like heat index and weather disparities influencing revisit intention, providing valuable insights for destination managers (Christodoulou et al., 2021). Twitter content was evaluated in a unique reputation generation system to determine credible reputation scores for products. Integrating sentiment orientation, user credibility, and tweet credibility, the system’s computed values are closely aligned with ground truth scores from various platforms. This suggests practical applications for consumers and businesses in decision-making processes on e-commerce platforms (Boumhidi & Nfaoui, 2021).

Analyzing Amazon and iHerb reviews, the research on sweetness in food products identified opportunities for less sweet products catering to a healthier consumer base. The study used manual curation, NLP, and machine learning to reveal the impact of sweetness on product liking, suggesting potential benefits for health-conscious customers and manufacturers (Asseo & Niv, 2022). Challenging the belief that longer product reviews are uniformly more helpful, the study utilized advanced machine learning methods to analyze Amazon reviews’ sentence-level argumentation. Contrary to prevailing views, longer reviews with frequent shifts between positive and negative arguments were perceived as less helpful, with implications for optimizing customer feedback systems and improving reviewer guidelines (Lutz, Pröllochs & Neumann, 2022).

The analysis of customer reviews for small domestic robots on Amazon addressed failure types and their impact on customer experience. Technical failures, particularly related to task completion and robustness, significantly impacted customer experience more than interaction or service failures. An NLP model predicted failure content in reviews, providing insights for prioritizing crucial issues for robotic system improvement (Honig et al., 2022). The study explored the memorable tourist experience (MTE) concept using TripAdvisor reviews, employing NLP and machine learning to analyze terms and relationships. Comparative analysis of UNESCO sites revealed shared MTE elements and validated hypotheses, emphasizing the value of reviews as supplementary data in tourism studies (Sánchez, 2022).

The impact of digitization on e-commerce was investigated through sentiment analysis of Amazon customer product reviews, utilizing SVM and deep learning techniques. The study provided valuable insights for businesses in the dynamic e-commerce market, indicating the effectiveness of both SVM and deep learning approaches in discerning sentiments (Arora, Srivastava & Ananda Kumar, 2022). Introducing the NLP-AHP method, the research assessed online shopping platform reviews through an empirical examination of microwave oven reviews on Amazon. The method swiftly identified crucial comments and temporal patterns, offering a valuable tool for data-driven decision-making to enhance product quality and refine sales strategies (Tang & Guo, 2022).

The analysis of Banglish text on social media in Bangladesh employed NLP techniques and machine learning models for product market demand assessment. Results indicated high accuracy in demand analysis, providing valuable insights into popular smartphone choices by gender in the Bangladeshi market (Hossain, Nayla & Rassel, 2022). The study on managerial responses to online customer complaints and negative reviews integrated justice theory and service recovery literature. Positive managerial responses influenced future review valence, with rational cues to procedural unfairness complaints enhancing future valence. The article provided insights for both theory and practical applications (Ravichandran & Deng, 2023).

An NLP analysis of Amazon reviews explored user satisfaction with physical activity trackers. Sentiment analysis and a Transformer-based language model classified technical aspects and user sentiments, revealing hidden perspectives on product satisfaction (Mantilla-Saltos et al., 2023). The study on TripAdvisor used deep learning models based on the Myers-Briggs Type Indicator (MBTI) to discern consumers’ personalities from electronic word-of-mouth (e-WOM). Findings linked specific discussion themes to personality traits, offering insights for personalized marketing messages and optimizing communication strategies (Christodoulou & Gregoriades, 2023).

The research addressed the challenge of assessing product quality in e-commerce, introducing the QLeBERT approach. Combining a quality-related lexicon, N-grams, BERT, and BiLSTM for classification, QLeBERT achieved better performance, providing a deeper understanding of textual input for predicting product quality (Ullah et al., 2023). An algorithm was introduced utilizing language-transformer technologies for automated product requirement generation from E-Shop reviews. The study showcased the transformative potential of transformer-enhanced opportunity mining in requirements engineering, efficiently extracting critical user needs from consumer reviews to enhance product improvement (Harth et al., 2023).

The impact of the “Amazon effect” on consumer perceptions of service attributes in offline/online retailers was explored. Analyzing social media comments using NLP, the study identified triggers for the Amazon effect, highlighting widespread dissatisfaction and reduced satisfaction with other retailers influenced by elevated consumer expectations shaped by Amazon (Vollero, Sardanelli & Siano, 2023). The study on CF recommendation systems utilized sentiment analysis on user reviews to derive implicit ratings, introducing novel approaches that demonstrated effectiveness in enhancing CF performance (Al-Ghuribi, Noah & Mohammed, 2023).

To address issues in review-based recommender systems, the article introduced the Time-Varying Attention with a Dual-Optimizer (TADO) model, combining a dual-optimizer network, BERT, and time-varying feature extraction. Tested on Amazon Product Reviews datasets, TADO outperformed state-of-the-art techniques by significant margins, offering improved classification and regression losses for enhanced performance (Li et al., 2023). Focusing on categorizing customer reviews on Amazon, the study employed machine learning techniques to enhance the e-commerce shopping experience. The model predicted sentiment, aiding users in making informed purchasing decisions by categorizing customer reviews based on inherent attributes (Harsha et al., 2023). The summary of existing literature on marketing and brand management is given in Table S6.