Fake consumer review detection using deep neural networks integrating word embeddings and emotion mining
Open accessThe DOI matches its Crossref record; 77 of the 77 references it cites were found in a registry or an index.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“Studies highlight that a substantial majority, around 80%, of consumers trust recommendations from fellow buyers with prior product experience (Hajek et al., 2020).”
From Reviews, trust, and customer experience in online marketplaces: the case of Mercado Libre Colombia (2024) · cites this paper as Hajek et al. (2020)
Citations
Cites
Distributed Representations of Words and Phrases and their Compositionality
Mikolov, T., Sutskever, I., Chen, K., Corrado, G., & Dean, J. (2013) · arXiv · doi:10.48550/arxiv.1310.4546 · Cited by 24,533 · cited 6×
“To create word embeddings, we used the Skip-Gram model [38, 50] trained on a large corpus of * 84 million Amazon reviews 3 [27].”
BackgroundMethodInfluentialMining and summarizing customer reviews
Hu, M., & Liu, B. (2004) · Proceedings of the tenth ACM SIGKDD international conference on Knowledge discovery and data mining · doi:10.1145/1014052.1014073 · Cited by 7,793 · cited 1×
“Polarity-based features were represented by the numbers of positive/negative words that match two popular lexicons, the OpinionFinder lexicon [11, 72] and Bing Liu’s opinion lexicon [29].”
BackgroundDistributed Representations of Sentences and Documents
Le, Q. V., & Mikolov, T. (2014) · arXiv (Cornell University) · doi:10.48550/arxiv.1405.4053 · Cited by 4,934 · cited 2×
“Their approach adopted word embeddings learnt using the continuous bag-of-words (CBOW) model [38, 50] so that semantically similar words are mapped to word vectors based on their context.”
MethodRecognizing contextual polarity in phrase-level sentiment analysis
Wilson, T., Wiebe, J., & Hoffmann, P. (2005) · Proceedings of the conference on Human Language Technology and Empirical Methods in Natural Language Processing - HLT '05 · doi:10.3115/1220575.1220619 · Cited by 3,345 · cited 1×
“Polarity-based features were represented by the numbers of positive/negative words that match two popular lexicons, the OpinionFinder lexicon [11, 72] and Bing Liu’s opinion lexicon [29].”
BackgroundSentiWordNet 3.0: An Enhanced Lexical Resource for Sentiment Analysis and Opinion Mining
Baccianella, S., Esuli, A., & Sebastiani, F. (2010) · Language Resources and Evaluation Conference (LREC) · doi:10.63317/2jktnrykui9s · Cited by 2,666 · cited 1×
“To estimate the strength, we employed the following resources: (1) AFINN [53], (2) S140 [36], (3) Sen-tiWordNet [4], (4) NRC Hashtag [36] and (5) Emoticons [53].”
MethodCROWDSOURCING A WORD–EMOTION ASSOCIATION LEXICON
Mohammad, S. M., & Turney, P. D. (2013) · Computational Intelligence · doi:10.1111/j.1467-8640.2012.00460.x · Cited by 2,634
García, S., Fernández, A., Luengo, J., & Herrera, F. (2010) · Information Sciences · doi:10.1016/j.ins.2009.12.010 · Cited by 2,229
He, R., & McAuley, J. (2016) · Proceedings of the 25th International Conference on World Wide Web · doi:10.1145/2872427.2883037 · Cited by 1,459
Finding Deceptive Opinion Spam by Any Stretch of the Imagination
Ott, M., Choi, Y., Cardie, C., & Hancock, J. T. (2011) · arXiv · doi:10.48550/arxiv.1107.4557 · Cited by 1,008 · cited 1×
“To overcome the problem of using these heuristic methods, Ott et al. [54] made the first effort to collate a fake review dataset with gold-standard fake reviews.”
Method(2014) · arXiv (Cornell University) · Cited by 942
Research works printed but not linked: 1
- BrightLocal (2018) Local consumer review survey 2018. https://www.brightlocal.com/research/local-consumer-review-survey/. Accessed 8 Nov 2019
Cited by
A survey on sentiment analysis methods, applications, and challenges
Wankhade, M., Rao, A. C. S., & Kulkarni, C. (2022) · Artificial Intelligence Review · doi:10.1007/s10462-022-10144-1 · Cited by 1,528
“Another disadvantage of all lexicon-based approaches (Hajek et al. 2020), including the dictionary-based approach, is finding opinion words specific for each domain as the polarity may vary.”
BackgroundMethodImpact of word embedding models on text analytics in deep learning environment: a review
Asudani, D. S., Nagwani, N. K., & Singh, P. (2023) · Artificial Intelligence Review · doi:10.1007/s10462-023-10419-1 · Cited by 274
“56% for fake consumer review detection (Hajek et al. 2020).”
Data Analytics for the Identification of Fake Reviews Using Supervised Learning
Alsubari, S. N. (2022) · Computers, Materials & Continua · doi:10.32604/cmc.2022.019625 · Cited by 254
“[33] applied two neural network models, deep feed-forward neural network and convolution neural network, based on the Amazon product review dataset.”
MethodBastick, Z. (2021) · Computers in Human Behavior · doi:10.1016/j.chb.2020.106633 · Cited by 205
From conflicts and confusion to doubts: Examining review inconsistency for fake review detection
Shan, G., Zhou, L., & Zhang, D. (2021) · Decision Support Systems · doi:10.1016/j.dss.2021.113513 · Cited by 128
Multimodal sentiment analysis: A survey
Lai, S., Hu, X., Xu, H., Ren, Z., & Liu, Z. (2023) · Displays · doi:10.1016/j.displa.2023.102563 · Cited by 134
Alzahrani, M. E., Aldhyani, T. H. H., Alsubari, S. N., Althobaiti, M. M., & Fahad, A. (2022) · Computational Intelligence and Neuroscience · doi:10.1155/2022/3840071 · Cited by 121
“Hajek et al. [25] developed a deep feedforward neural network and convolution model to detect fake positive and negative review in an Amazon dataset.”
Hamed, S. K., Aziz, M. J. A., & Yaakub, M. R. (2023) · Heliyon · doi:10.1016/j.heliyon.2023.e20382 · Cited by 145
“Visual diversity score, clustering score, similarity distribution histogram, clarity score, and coherence score are some of the most significant visual features of a given piece of visual news material [19].”
BackgroundInfluentialFake review detection in e-Commerce platforms using aspect-based sentiment analysis
Hájek, P., Hikkerova, L., & Sahut, J. (2023) · Journal of Business Research · doi:10.1016/j.jbusres.2023.114143 · Cited by 89
Improving spam email classification accuracy using ensemble techniques: a stacking approach
Adnan, M., Imam, M. O., Javed, M. F., & Murtza, I. (2023) · International Journal of Information Security · doi:10.1007/s10207-023-00756-1 · Cited by 62
“They also used unsupervised topic modeling technique for the similar problem [13].”
Building Fake Review Detection Model Based on Sentiment Intensity and PU Learning
Zhang, S., Zhu, A., Guangli, Z., Wei, Z., & Li, K. (2023) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2023.3234427 · Cited by 66
Speech emotion recognition and text sentiment analysis for financial distress prediction
Hájek, P., & Munk, M. (2023) · Neural Computing and Applications · doi:10.1007/s00521-023-08470-8 · Cited by 82
“It was considered that text emotional features would usefully supplement and extend both the speech emotions and the sentiment analysis, as reported in previous business research [25, 31].”
ResultSelf-citationAlsubari, S. N., Deshmukh, S. N., Al-Adhaileh, M. H., Alsaade, F. W., & Aldhyani, T. H. H. (2021) · Applied Bionics and Biomechanics · doi:10.1155/2021/5522574 · Cited by 60
“Based on Amazon electronic product review dataset, Hajek et al. [19] have implemented two neural network methods that were Deep Feed-Forward Neural Network and convolution neural network.”
MethodRetractedWord-level emotion distribution with two schemas for short text emotion classification
Li, Z., Xie, H., Cheng, G., & Li, Q. (2021) · Knowledge-Based Systems · doi:10.1016/j.knosys.2021.107163 · Cited by 55
Detecting fake reviews through topic modelling
Birim, Ş. Ö., Kazançoğlu, İ., Mangla, S. K., Kahraman, A., Kumar, S., & Kazançoğlu, Y. (2022) · Journal of Business Research · doi:10.1016/j.jbusres.2022.05.081 · Cited by 69
Hájek, P., & Sahut, J. (2022) · Technological Forecasting and Social Change · doi:10.1016/j.techfore.2022.121532 · Cited by 70
T-Miner: A Generative Approach to Defend Against Trojan Attacks on DNN-based Text ClassificationPreprint
Azizi, A., Tahmid, I. A., Waheed, A., Mangaokar, N., Pu, J., Javed, M., Reddy, C. K. A., & Viswanath, B. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2103.04264 · Cited by 127
“Deep Neural Networks (DNNs) have significantly advanced the domain of natural language processing, including classification tasks such as detecting and removing toxic content on online platforms [19], evaluating crowd sentiment [44], and detecting fake reviews/comments [24, 50].”
BackgroundVergaray, A. D., Rueda, N. D. G., Sánchez, M. S. A., Robles-Espiritu, W., & Quiñones, M. E. C. (2024) · International Journal of Information Management Data Insights · doi:10.1016/j.jjimei.2024.100267 · Cited by 108
Gupta, P., Gandhi, S., & Chakravarthi, B. R. (2021) · Forum for Information Retrieval Evaluation · doi:10.1145/3503162.3503169 · Cited by 46
“Researchers in [5] proposed neural network models trained using high-dimensional feature representation to classify reviews into fake and genuine categories.”
BackgroundEspina-Romero, L. C., Sánchez, J. G. N., Hurtado, H. G., Conde, H. O. D., Castro, Y. S., Cajo, L. E. C., & Corredoira, J. R. (2023) · Sustainability · doi:10.3390/su151612176 · Cited by 60
Fake Online Reviews: A Unified Detection Model Using Deception Theories
Abdulqader, M., Namoun, A., & Alsaawy, Y. (2022) · IEEE Access · doi:10.1109/access.2022.3227631 · Cited by 54
“Some studies [170], [171] have used word embedding with deep learning to detect fake reviews.”
BackgroundResearch on false review detection Methods: A state-of-the-art review
Mewada, A., & Dewang, R. K. (2021) · Journal of King Saud University - Computer and Information Sciences · doi:10.1016/j.jksuci.2021.07.021 · Cited by 44
“…applied word embedding models (Kumar, 2003; Zhang et al., 2016; Cao et al., 2020; Hernandez-Castaneda and Calvo, 2017) and neural network models (Hajek et al., 2020; Anass et al., 2020; Fahfouh et al., 2020; Ren and Ji, 2017; Li et al., 2017; Sun et al., 2016) to obtain the text representation…”
Reviews, trust, and customer experience in online marketplaces: the case of Mercado Libre Colombia
Peña-García, N., Losada-Otálora, M., Auza, D. P., & Cruz, M. P. (2024) · Frontiers in Communication · doi:10.3389/fcomm.2024.1460321 · Cited by 38
Duma, R. A., Niu, Z., Nyamawe, A. S., Tchaye-Kondi, J., & Yusuf, A. A. (2023) · Soft Computing · doi:10.1007/s00500-023-07897-4 · Cited by 41
“• DFFNN (Hajek et al. 2020): They used DFFNN in integrating review word embedding vectors (n-gram features) and the emotion feature.”
MethodManaskasemsak, B., Tantisuwankul, J., & Rungsawang, A. (2021) · Neural Computing and Applications · doi:10.1007/s00521-021-05948-1 · Cited by 42
Detecting fake reviews with supervised machine learning algorithms
Lee, M., Song, Y. H., Li, L., Lee, K. Y., & Yang, S. (2022) · Service Industries Journal · doi:10.1080/02642069.2022.2054996 · Cited by 43
“Some of the speci fi c linguistic cues that have been examined in extant studies on the detection of fake online reviews include a ff ective cues (e.g. Hajek et al., 2020; Li et al., 2020; Ott et al., 2011), cognitive cues (e.g. Banerjee et al., 2015; Matsumoto and Hwang, 2015; Wahyuni and Djunaidy,…”
BackgroundA Novel Quantum Neural Network Approach to Combating Fake Reviews
Bikku, T., Thota, S., & Shanmugasundaram, P. (2024) · The International journal of networked and distributed computing · doi:10.1007/s44227-024-00028-x · Cited by 34
Detecting Fake Reviews Using Multidimensional Representations With Fine-Grained Aspects Plan
Liu, M., Shang, Y., Yue, Q., & Zhou, J. (2020) · IEEE Access · doi:10.1109/access.2020.3047947 · Cited by 32
“DFFNN [19]: It is a deep feedforward neural network that combines bag-of-words, n-gram features of comment text, word embedding, and multiple emotion indicators to create representations.”
BackgroundMethodRHGNN: Fake reviewer detection based on reinforced heterogeneous graph neural networks
Zhao, J., Shao, M., Tang, H., Liu, J., Du, L., & Wang, H. (2023) · Knowledge-Based Systems · doi:10.1016/j.knosys.2023.111029 · Cited by 43
Fake review detection techniques, issues, and future research directions: a literature review
Duma, R. A., Niu, Z., Nyamawe, A. S., Tchaye-Kondi, J., Jingili, N., Yusuf, A. A., & Deve, A. F. (2024) · Knowledge and Information Systems · doi:10.1007/s10115-024-02118-2 · Cited by 47
“Considering the semantic meaning of the review and emotions hidden in the review [65] proposed two deep NN models (i.e., CNN and deep feed-forward neural network (DFFNN)) that learn from review document-level representation integrating three features: consumer emotion indicators, n-grams, word…”
Ganesh, D., Rao, K. J., Kumar, M., Vinitha, M., Anitha, M., Likith, S. S., & Taralitha, R. (2023) · International Conference on Sustainable Computing and Data Communication Systems (ICSCDS) · doi:10.1109/icscds56580.2023.10104856 · Cited by 31
“You are cautioned that Samuel Levine, director of the FTC's Bureau of Consumer Protection, stated: "Advertisers pay the price for engaging in these misleading activities[3-7]."”
BackgroundOnline Fake News Detection Using Machine Learning Techniques: A Systematic Mapping Study
Lahby, M., Aqil, S., Yafooz, W. M. S., & Abakarim, Y. (2021) · Studies in computational intelligence · doi:10.1007/978-3-030-90087-8_1 · Cited by 34
Disinformation detection on social media: An integrated approach
Rastogi, S., & Bansal, D. (2022) · Multimedia Tools and Applications · doi:10.1007/s11042-022-13129-y · Cited by 36
Ramezani, E. (2025) · Neurocomputing · doi:10.1016/j.neucom.2025.129862 · Cited by 41
Graph Learning for Fake Review Detection
Yu, S., Ren, J. F., Li, S., Naseriparsa, M., & Xia, F. (2022) · Frontiers in Artificial Intelligence · doi:10.3389/frai.2022.922589 · Cited by 30
“Hajek et al. (2020) explore the importance of hidden emotions contained in review texts.”
BackgroundA comprehensive survey of various methods in opinion spam detection
Mewada, A., & Dewang, R. K. (2022) · Multimedia Tools and Applications · doi:10.1007/s11042-022-13702-5 · Cited by 32
“…Bag-Of-Words HRD Accuracy 84% Bagging [131] Word Embedding, N-Gram HRD Accuracy 78% LSTM [160] Sentence Three Partition HRD Accuracy 83% CNN [49] Bag-of-Words, Word Context, User Emotions HRD Accuracy 87% KNN-SVM [30] Unigram Movie Review Accuracy 82% Self-Training-NB [86] N-gram, TF-IDF,…”
BackgroundLu, J., Zhan, X., Liu, G., Zhan, X., & Deng, X. (2023) · Electronics · doi:10.3390/electronics12102165 · Cited by 32
“Hajek et al. [21] introduced an enhanced DFFNN model that considered the impacts of various word, sentence, and sentiment representations on the detection of fake reviews.”
Deep Fake Recognition in Tweets Using Text Augmentation, Word Embeddings and Deep Learning
Tesfagergish, S. G., Damaševičius, R., & Kapočiūtė-Dzikienė, J. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-86979-3_37 · Cited by 25
Wang, N., Yang, J., Kong, X., & Gao, Y. (2021) · Expert Systems with Applications · doi:10.1016/j.eswa.2021.116207 · Cited by 26
Multiscale cascaded domain-based approach for Arabic fake reviews detection in e-commerce platforms
Qandos, N., Hamad, G., Alharbi, M., Alturki, S., Alharbi, W. K., & Albelaihi, A. (2024) · Journal of King Saud University - Computer and Information Sciences · doi:10.1016/j.jksuci.2024.101926 · Cited by 23
“(Hajek et al., 2020) implemented two Neural Networks (NN) models, the Deep FeedForward Neural Networks (DFFNN) and the Convolutional Neural Networks (CNN) with the integration of bag-of-words, emotion representations, and word embeddings.”
Shilling Attacks and Fake Reviews Injection: Principles, Models, and Datasets
Nawara, D., Aly, A., & Kashef, R. F. (2024) · IEEE Transactions on Computational Social Systems · doi:10.1109/tcss.2024.3465008 · Cited by 33
Detecting fake review intentions in the review context: A multimodal deep learning approach
Hou, J., Tan, Z., Zhang, S., Hu, Q., & Wang, P. (2025) · Electronic Commerce Research and Applications · doi:10.1016/j.elerap.2025.101485 · Cited by 28
Hájek, P., Barushka, A., & Munk, M. (2021) · International Journal of Neural Systems · doi:10.1142/s0129065721500131 · Cited by 24
“ment and semantic representations may further improve classification performance in related tasks due to highly domain-specific context.(44,45) Product and”
BackgroundSelf-citationBERT-Based Deceptive Review Detection in Social Media: Introducing DeceptiveBERT
Hyder, S. B., Tariq, N., Moqurrab, S. A., Ashraf, M. I., Yoo, J., & Srivastava, G. (2024) · IEEE Transactions on Computational Social Systems · doi:10.1109/tcss.2024.3403937 · Cited by 29
“Hajek et al. [16] developed DNN models using high-dimensional feature representation, outperforming existing approaches.”
Jacob, M. S., & Rajendran, P. S. (2021) · Concurrency and Computation Practice and Experience · doi:10.1002/cpe.6539 · Cited by 27
“Hajek et al. 37 detected the fake consumer review using deep neural networks (DNNs) namely the deep feed-forward neural network (DFFNN) and convolutional neural network (CNN).”
Detecting Fake Online Reviews using Fine-tuned BERT
Refaeli, D., & Hájek, P. (2021) · International Conference on E-Business and Internet (ICEBI) · doi:10.1145/3497701.3497714 · Cited by 29
Hossain, M. R., Hoque, M. M., Siddique, N. H., & Sarker, I. H. (2023) · Neural Computing and Applications · doi:10.1007/s00521-023-08442-y · Cited by 20
“disinformation detection using statistical ML and transformer-based learning [28].”
MethodKronrod, A., Gordeliy, I., & Lee, J. K. (2022) · Journal of Consumer Research · doi:10.1093/jcr/ucac056 · Cited by 26
FRD-LSTM: a novel technique for fake reviews detection using DCWR with the Bi-LSTM method
Qayyum, H., Ali, F., Nawaz, M., & Nazir, T. (2023) · Multimedia Tools and Applications · doi:10.1007/s11042-023-15098-2 · Cited by 19
“For a fair comparison, the average results of the proposed approach are compared with the selected studies discussed in [5, 7, 13, 17].”
MethodResultInfluentialAmazon product recommendation system based on a modified convolutional neural network
Latha, Y. M., & Rao, B. S. (2024) · ETRI Journal · doi:10.4218/etrij.2023-0162 · Cited by 24
“Hajek and others [21] integrated consumer emotions, word context, and a bag of words for fake review detection.”
BackgroundEnhancing Cybersecurity with Transformers: Preventing Phishing Emails and Social Media Scams
Daoud, E. A., Daoud, L. A., Asassfeh, M., Al-Shaikh, A., Al-Sherideh, A. S., & Afaneh, S. (2024) · IEEE Conference on Dependable and Secure Computing (DSC) · doi:10.1109/dsc63325.2024.00017 · Cited by 19
Alsharif, N. H. (2022) · Soft Computing · doi:10.1007/s00500-022-06806-5 · Cited by 17
“Based on Amazon’s electronic product review dataset, Hajek et al. (2020) implemented two neural network models: the deep feedforward neural network (DFFN) and the convolution neural network (CNN).”
MethodRetractedLi, S., Zhong, G., Jin, Y., Wu, X., Zhu, P., & Wang, Z. (2022) · IEEE Transactions on Computational Social Systems · doi:10.1109/tcss.2022.3144013 · Cited by 18
“Hajek et al. [11] proposed deep feed-forward neural network (DFFNN) and convolutional neural network (CNN) models and combined the traditional word bag, the context of the word, and the consumers’ emotion; these deceptive review detection systems performed well on all datasets.”
BackgroundA Contextual Relationship Model for Deceptive Opinion Spam Detection
Fahfouh, A., Riffi, J., Mahraz, M. A., Yahyaouy, A., & Tairi, H. (2022) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2022.3183037 · Cited by 16
“Besides, Hajek and Munk [34] proposed two deep neural network models to detect fake consumer reviews.”
BackgroundExplainable knowledge integrated sequence model for detecting fake online reviews
Han, S. Y., Wang, H., Li, W., Zhang, H., & Zhuang, L. (2022) · Applied Intelligence · doi:10.1007/s10489-022-03822-8 · Cited by 18
“To evaluate the effectiveness of the proposed model, we further compare the proposed model with the latest state-of-the-art methods, including SVM [17], CNN [16], DFFNN [17], LDA − BP ⊕ T extCNN [33], BERT [34], MFNN [35] and SOM-CNN [36].”
MethodInfluentialAl-Zoubi, A. M., Mora, A. M., & Faris, H. (2023) · IEEE Access · doi:10.1109/access.2023.3293641 · Cited by 20
“For example, the authors of [51] proposed two neural network models that successfully detect fake reviews by taking into account the word context and the consumer’s emotional state as well as traditional bag-of-words methods.”
BackgroundAdvancing Email Spam Classification using Machine Learning and Deep Learning Techniques
Alsuwit, M. H., Haq, M. A., & Aleisa, M. A. (2024) · Engineering Technology & Applied Science Research · doi:10.48084/etasr.7631 · Cited by 28
“Authors in [13] developed a DL model that utilized features like character n-grams and word embeddings, alongside an unsupervised topic modeling technique, for addressing a similar challenge.”
MethodFNG-IE: an improved graph-based method for keyword extraction from scholarly big-data
Tahir, N., Asif, M., Ahmad, S., Malik, M. S. A., Aljuaid, H., Butt, M. A., & Rehman, M. (2021) · PeerJ Computer Science · doi:10.7717/peerj-cs.389 · Cited by 18
Enhancing representation in the context of multiple-channel spam filtering
Novo-Lourés, M., Ruano-Ordás, D., Pavón, R., Laza, R., Gómez-Meire, S., & Méndez, J. R. (2021) · Information Processing & Management · doi:10.1016/j.ipm.2021.102812 · Cited by 18
“Word embedding (Hajek, Barushka & Munk, 2020) schemes ( iii ) are based on using contextual information of words in large document collections to create models able to predict the most probable word in a given context.”
BackgroundDeterminants of fake news diffusion on social media: a systematic literature review
Shahzad, K., Khan, S. A., Iqbal, A., Shabbir, O., & Latif, M. (2023) · Global Knowledge, Memory and Communication · doi:10.1108/gkmc-06-2023-0189 · Cited by 24
Geetha, S., Elakiya, E., Kanmani, R. S., & Das, M. K. (2025) · Scientific Reports · doi:10.1038/s41598-025-89453-8 · Cited by 15
MUSH: Multi-Stimuli Hawkes Process Based Sybil Attacker Detector for User-Review Social Networks
Qu, Z., Lyu, C., & Chi, C. (2022) · IEEE Transactions on Network and Service Management · doi:10.1109/tnsm.2022.3186513 · Cited by 17
“Based on previous research [14], [51], [52], we extract four traditional features of user behaviors: the average rating, the number of reviews, the rating deviation, and the average number of reviews within the time window.”
MethodSpammer group detection and diversification of customers’ reviews
Hussain, N., Mirza, H. T., Ali, A. H., Iqbal, F., Hussain, I., & Kaleem, M. (2021) · PeerJ Computer Science · doi:10.7717/peerj-cs.472 · Cited by 15
Fake Review Detection Model Based on Comment Content and Review Behavior
Sun, P., Bi, W., Zhang, Y., Wang, Q., Kou, F., Lu, T., & Chen, J. (2024) · Electronics · doi:10.3390/electronics13214322 · Cited by 30
DISINFORMATION DETECTION ABOUT ISLAMIC ISSUES ON SOCIAL MEDIA USING DEEP LEARNING TECHNIQUES
Hamed, S. K., Aziz, M. J. A., & Yaakub, M. R. (2023) · Malaysian Journal of Computer Science · doi:10.22452/mjcs.vol36no3.3 · Cited by 17
“Content-based deep learning models in detecting fake news mean that they rely mainly on features that a classifier can extract from content [34], such as linguistic features, syntactic features [25], or sentiment-based features [35].”
BackgroundAsudani, D. S., Nagwani, N. K., & Singh, P. (2022) · Data Technologies and Applications · doi:10.1108/dta-07-2021-0191 · Cited by 14
Hakami, N. A., & Mahmoud, H. A. H. (2022) · Sustainability · doi:10.3390/su141912860 · Cited by 15
Duma, R. A., Niu, Z., Nyamawe, A. S., Tchaye-Kondi, J., Chambua, J., & Yusuf, A. A. (2023) · Multimedia Tools and Applications · doi:10.1007/s11042-023-15193-4 · Cited by 13
“• CNN [33]: They used CNN in integrating review word embedding vectors (n-gram features) and emotion features.”
InfluentialSentiment Analysis for E-commerce Product Reviews: Current Trends and Future DirectionsPreprint
Elzeheiry, S. A., Gab-Allah, W. A., Mekky, N. E., & Elmogy, M. M. (2023) · Preprints.org · doi:10.20944/preprints202305.1649.v1 · Cited by 22
A Hybridized Approach for Enhanced Fake Review Detection
Xu, S., Cuan, H., Yin, Z., & Yin, C. (2024) · IEEE Transactions on Computational Social Systems · doi:10.1109/tcss.2024.3411635 · Cited by 15
“For example, Hajek et al. [15] improve feedforward neural networks to mine sentiment information; Li et al. [16] improve convolutional neural networks to learn document-level representations of reviews; Ren and Ji [17] and Liu et al. [10] improve recurrent neural networks to mine global semantic…”
Handling consumer vulnerability in e-commerce product images using machine learning
Chatrath, S. K., Batra, G., & Chaba, Y. (2022) · Heliyon · doi:10.1016/j.heliyon.2022.e10743 · Cited by 12
“New neural network models that combine the conventional bag-of-words, word context, and user emotions have been proposed by (Petr Hajek et al., 2020).”
BackgroundReddy, B. R. R., & Kumar, R. L. (2024) · Computers, materials & continua/Computers, materials & continua (Print) · doi:10.32604/cmc.2024.057071 · Cited by 12
A new multilingual framework for fake reviews detection based on a large language model
Mohawesh, R., AlQarni, A. A., Alkhushayni, S. M., Daradkeh, T., & Salameh, H. B. (2025) · The Journal of Supercomputing · doi:10.1007/s11227-025-07636-6 · Cited by 12
“Word embeddings, emotion representations, and bag-of-words were utilized by Convolutional Neural Networks (CNNs) and Deep FeedForward Neural Networks (DFFNNs) in the study by Hajek et al. [23].”
Opinion spam detection using Deep Learning
Bathla, G., & Kumar, A. (2021) · International Conference on Signal Processing and Integrated Networks (SPIN) · doi:10.1109/spin52536.2021.9566048 · Cited by 12
Fake Review Detection Using Sentiment Analysis and Deep Learning
Shetgaonkar, P. R., Rodrigues, J. T., Aswale, S., Gonsalves, V. L. K., Rodrigues, J. C., & Naik, A. (2021) · International Conference on Technological Advancements and Innovations (ICTAI) · doi:10.1109/ictai53825.2021.9673375 · Cited by 12
Detecting Fake Reviews in Google Maps—A Case Study
Gryka, P., & Janicki, A. (2023) · Applied Sciences · doi:10.3390/app13106331 · Cited by 13
Determinants of multimodal fake review generation in China’s E-commerce platforms
Liu, C., He, X., & Yi, L. (2024) · Scientific Reports · doi:10.1038/s41598-024-59236-8 · Cited by 21
Leveraging Stacking Framework for Fake Review Detection in the Hospitality Sector
Ashraf, S. A., Javed, A. F., Bellary, S., Bala, P. K., & Panigrahi, P. K. (2024) · Journal of theoretical and applied electronic commerce research · doi:10.3390/jtaer19020075 · Cited by 15
“[55] leveraged the capability of deep learning architectures and proposed a high-dimensional model conflating n-gram, skip-gram, and emotion-based features.”
BackgroundWang, Z., Yao, A., Xu, G., & Ren, M. (2025) · Information Processing & Management · doi:10.1016/j.ipm.2025.104352 · Cited by 10
Opinion Mining of Consumer Reviews Using Deep Neural Networks with Word-Sentiment Associations
Hájek, P., Barushka, A., & Munk, M. (2020) · IFIP advances in information and communication technology · doi:10.1007/978-3-030-49161-1_35 · Cited by 10
“Moreover, the hybrid representation models combining word embeddings with the traditional bag-of-words representation may further improve the classification performance in related tasks due to highly domain-specific context [18, 19].”
BackgroundMethodSelf-citationLarge language model meets chaos: A new deep learning model for fake review detection
Fan, Y., Fan, H., Zhang, F., & Wang, Z. (2025) · Electronic Commerce Research and Applications · doi:10.1016/j.elerap.2025.101521 · Cited by 9
Detecting deception: employing deep neural networks for fraudulent review detection on Amazon
Jayasinghe, J. M. T., & Dassanayaka, S. (2025) · Neural Computing and Applications · doi:10.1007/s00521-025-11485-y · Cited by 17
“Mukherjee et al. and Hajek et al. conducted significant research on fake review detection using diverse datasets and machine learning approaches [3, 16].”
FakeX: A Framework for Detecting Fake Reviews of Browser Extensions
Olsson, E., Eriksson, B., Picazo‐Sanchez, P., Andersson, L., & Sabelfeld, A. (2024) · ACM Asia Conference on Computer and Communications Security (ASIA CCS) · doi:10.1145/3634737.3656999 · Cited by 12
“Other solutions are based on the links of the reviewers, reviews, products, and merchants [10], or the sentiment analysis of the reviews [20, 33].”
Fake Review Detection Using Rating-Sentiment Inconsistency
Sharifpour, K., & Lahmiri, S. (2023) · International Conference on Machine Learning and Applications · doi:10.1109/icmla58977.2023.00137 · Cited by 9
Shang, Y., Liu, M., Zhao, T., & Zhou, J. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-86383-8_33 · Cited by 9
Convolutional Neural Networks- Bidirectional Long Short Term Memory Based Fake Review Classification
Reddy, R., & Kumar, U. M. A. (2022) · International Conference on Intelligent Computing and Control Systems (ICICCS) · doi:10.1109/iciccs53718.2022.9788307 · Cited by 10
Hamed, S. K., Aziz, M. J. A., & Yaakub, M. R. (2023) · International Journal of Advanced Computer Science and Applications · doi:10.14569/ijacsa.2023.0140742 · Cited by 15
“The larger size of the dataset [41], more diverse [42], more feature-rich [43], and low-noise [44], leads to improving the model's performance and increases its accuracy in identifying fake news [40].”
BackgroundA survey of sentiment analysis methods based on graph neural network
Rad, R. A., Yamaghani, M. R., & Nourbakhsh, A. (2025) · International Journal of Data Science and Analytics · doi:10.1007/s41060-025-00714-1 · Cited by 12
Huang, J.-Y., & Lee, W. (2022) · Knowledge-Based Systems · doi:10.1016/j.knosys.2022.108425 · Cited by 10
A metadata-aware detection model for fake restaurant reviews based on multimodal fusion
Jian, Y., Chen, X., Wang, X., Liu, Y., Chen, X., Lan, X., Wang, W., & Wang, H. (2024) · Neural Computing and Applications · doi:10.1007/s00521-024-10647-8 · Cited by 8
Fake Restaurant Review Detection Using Deep Neural Networks with Hybrid Feature Fusion Method
Jian, Y., Chen, X., & Wang, H. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-00129-1_9 · Cited by 7
Automated Design of the Deep Neural Network Pipeline
Gerber, M., & Pillay, N. (2022) · Applied Sciences · doi:10.3390/app122312215 · Cited by 7
Detecting Spam Product Reviews in Roman Urdu Script
Hussain, N., Mirza, H. T., Iqbal, F., Hussain, I., & Kaleem, M. (2020) · The Computer Journal · doi:10.1093/comjnl/bxaa164 · Cited by 7
Fake Review Detection Using Hybrid Ensemble Learning
Hegde, S. B., Rai, R. R., Hiremath, P. G. S., & Gangisetty, S. (2021) · Lecture notes in electrical engineering · doi:10.1007/978-981-33-6987-0_22 · Cited by 7
Rule-Based Classifiers for Identifying Fake Reviews in E-commerce: A Deep Learning System
Alsubari, S. N., Deshmukh, S. N., Aldhyani, T. H. H., Al-Nefaie, A. H. A., & Alrasheedi, M. A. (2023) · Forum for interdisciplinary mathematics · doi:10.1007/978-981-19-8566-9_14 · Cited by 12
Su, Z., Yang, M., Zhai, Q., Guo, K., Huang, Y., & Cong, Y. (2025) · Scientific Reports · doi:10.1038/s41598-025-86551-5 · Cited by 11
(2022) · International journal of intelligent engineering and systems · doi:10.22266/ijies2022.1031.41 · Cited by 6
“Hajek [11] applied two neural networks to integrate emotions of consumers and bag-of-words.”
BackgroundMethodBoosting Accuracy of Fake Review Prediction Using Synthetic Minority Oversampling Technique
Saxena, B., Goyal, S., Kumari, A., & Agarwal, A. (2022) · International Conference on Computing, Communication, and Intelligent Systems (ICCCIS) · doi:10.1109/icccis56430.2022.10037717 · Cited by 7
“Hajek et al. [10] applied a deep feed-forward neural network (DFNN) and a CNN on a product review dataset to extract word emotions and N-grams.”
BackgroundSasikala, C., Ramya, S., Rajeshkumar, S., Ramachandramoorthy, K. B., VijayaKumar, S., & Umapathi, K. (2023) · International Conference on Pervasive Computing and Social Networking (ICPCSN) · doi:10.1109/icpcsn58827.2023.00071 · Cited by 6
“Kashyap Popat [3] proposes an end-to-end neural network model for automated fact-checking of textual claims in order to combat misinformation and fake news.”
BackgroundIs it fake or not? A comprehensive approach for multimodal fake news detection
Mura, D. A., Usai, M., Loddo, A., Sanguinetti, M., Zedda, L., Ruberto, C. D., & Atzori, M. (2025) · Online Social Networks and Media · doi:10.1016/j.osnem.2025.100314 · Cited by 9
Metadata
- Authors
- Hajek, P., Barushka, A., & Munk, M.
- Affiliations
- University of Pardubice (CZ)
- Constantine the Philosopher University in Nitra (SK)
- Venue
- Neural Computing and Applications
- Published
- 2020-02-01
- Volume
- 32
- Issue
- 23
- Pages
- 17259-17274
- ISSN
- 0941-0643 (ISSN-L)
- 1433-3058
- OpenAlex
- W3003892205
- Semantic Scholar
- fb0aaa854f882a9a72eb5c0600cc08b781aa422c
- Cited by
- 186
- References
- 77
- Citations by year
- 2026: 10 · 2025: 29 · 2024: 38 · 2023: 41 · 2022: 33 · 2021: 30 · 2020: 5
- FWCI
- 25.64
- Type
- journal article
- Language
- en
- Open access
- green
- hdl.handle.net
- Licence
- other-oa
- www.springer.com/tdm (tdm)
- www.springer.com/tdm (vor)
- Locations
- Neural Computing and Applications (publishedVersion)
- Digitální knihovna Univerzity Pardubice (Univerzity Pardubice) (submittedVersion, other-oa)
- Funders
- Grantová Agentura České Republiky (19-15498S)
- European Regional Development Fund (Fake news on the Internet - identification, content analysis, emotions)
- Topics
- Physical Sciences › Computer Science › Information Systems › Spam and Phishing Detection
- Social Sciences › Sociology and Political Science › Misinformation and Its Impacts
- Physical Sciences › Computer Science › Artificial Intelligence › Sentiment Analysis and Opinion Mining
- Keywords
- fake review detection, consumer reviews, word embeddings, emotion lexicon, emotion analysis, n-grams, bag-of-words features, text classification, e-commerce fraud
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.