Skip to main content

Advertisement

Springer Nature Link
Log in

Sentiment analysis deep learning model based on a novel hybrid embedding method

  • Original Article
  • Published:
Social Network Analysis and Mining Aims and scope Submit manuscript

Abstract

(WE) are crucial for capturing the meanings of words, offering continuous vector representations that encode both semantic and syntactic information. In this paper, we present a novel approach called WordFast, which combines the strengths of FastText and Word2Vec through a linear combination method. The WordFast approach aims to enhance the performance of WE, particularly in the context of sentiment analysis (SA). SA has become a prominent area of research in Natural Language Processing (NLP), especially when it comes to analyzing user opinions on digital platforms. Our proposed (SA) deep model is based on the WordFast method and incorporates two variations of Recurrent Neural Network (RNN) architectures. This model is tested using two datasets: IMDB reviews and Amazon reviews.The outcomes produced by the WordFast method are classified using Gated Recurrent Unit (GRU) and Long Short-Term Memory (LSTM) models.Our experiments reveal a significant improvement in accuracy when analyzing real IMDB, achieving 88.75/% and 89.54%, as well as real Amazon reviews, with accuracies of 94.69% and 94.89%.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Algorithm 1
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12

Similar content being viewed by others

Data availability

No datasets were generated or analysed during the current study.

Notes

  1. https://www.rottentomatoes.com.

  2. https://www.kaggle.com/bittlingmayer/amazonreviews.

References

  • Alharbi NM, Alghamdi NS, Alkhammash EH, Al Amri JF (2021) Evaluation of sentiment analysis via word embedding and RNN variants for Amazon online reviews. Math Prob Eng 2021(1):5536560

    MATH  Google Scholar 

  • Ali H, Hashmi E, Yayilgan Yildirim S, Shaikh S (2024) Analyzing amazon products sentiment: a comparative study of machine and deep learning, and transformer-based techniques. Electronics 13:1305

    Google Scholar 

  • Alroobaea R (2022) Sentiment analysis on amazon product reviews using the recurrent neural network (rnn). Int J Adv Comput Sci Appl 13(4):1

    Google Scholar 

  • Alsharef A, Aggarwal K, Sonia X, Koundal D, Alyami H, Ameyed D (2022) An automated toxicity classification on social media using LSTM and word embedding. Comput Intell Neurosci 1:8467349

    Google Scholar 

  • Ayata D, Saraçlar M, Özgür A (2017) Turkish tweet sentiment analysis with word embedding and machine learning .25th signal processing and communications applications conference (SIU):1-4 IEEE

  • Başarslan MS, Kayaalp F (2023) MBi-GRUMCONV: a novel multi Bi-GRU and multi CNN-based deep learning model for social media sentiment analysis. J Cloud Comput 12(1):5

    Google Scholar 

  • Bodapati JD, Veeranjaneyulu N, Shareef SN (2019) Sentiment analysis from movie reviews using LSTMs. Ingénierie des Systèmes d Inf 24(1):125–129

    Google Scholar 

  • Bojanowski P, Grave E, Joulin A, Mikolov T (2017) Enriching word vectors with subword information. Trans Assoc Comput Linguist 5:135–146

    Google Scholar 

  • Chiny Mohamed et al (2023) Effect of word embedding vector dimensionality on sentiment analysis through short and long texts. IAES Int J Artif Intell 12(2):823

    MATH  Google Scholar 

  • Dang NC, Moreno-García MN, De la Prieta F (2020) Sentiment analysis based on deep learning: a comparative study. Electronics 9(3):483

    MATH  Google Scholar 

  • Devlin J, Chang MW, Lee K, Toutanova K (2019) Bert:pre-training of deep bidirectional transformers for language understanding. In: Proceedings of NAACL-HLT 5: 4171– 4186

  • González-Santos C, Vega-Rodríguez MA, Pérez CJ, López-Muñoz JM, Martínez-Sarriegui I (2023) Automatic assignment of moral foundations to movies by word embedding. Knowl-Based Syst 270:110539

    Google Scholar 

  • Haddad O, Fkih F, Omri MN (2024) An intelligent sentiment prediction approach in social networks based on batch and streaming big data analytics using deep learning. Netw Anal Min 14:150

    Google Scholar 

  • Hassan A, Mahmood A () Deep learning approach for sentiment analysis of short texts. In: Proceedings of the third international conference on control, automation and robotics (ICCAR) Nagoya, Japan, pp 705–710

  • Huang W, Rao G, Feng Z, Cong Q (2018) LSTM with sentence representations for document-level sentiment classification. Neurocomputing 49:308

    MATH  Google Scholar 

  • Incitti F, Urli F, Snidaro L (2023) Beyond word embeddings: a survey. Inf Fusion 89:418–436

    MATH  Google Scholar 

  • Islam MS, Kabir MN, Ghani NA et al (2024) Challenges and future in deep learning for sentiment analysis: a comprehensive review and a proposed novel hybrid approach. Artif Intell Rev 57:62

    MATH  Google Scholar 

  • Jain PK, Pamula R, Srivastava G (2021) A systematic literature review on machine learning applications for consumer sentiment analysis using online reviews. Comput Sci Rev 41:100413

    MATH  Google Scholar 

  • Jiang Z, Gao B, He Y, Han Y, Doyle P, Zhu Q (2021) Text classification using novel term weighting scheme-based improved TF-IDF for internet media reports. Math Prob Eng 2021(1):6619088

    Google Scholar 

  • Johnson SJ, Murty MR, Navakanth I (2024) A detailed review on word embedding techniques with emphasis on word2vec. Multimed Tools Appl 83(13):37979–38007

    Google Scholar 

  • Kamyab M, Liu G, Adjeisah M (2021) Attention-based CNN and Bi-LSTM model based on TF-IDF and GloVe word embedding for sentiment analysis. Appl Sci 11:11255. https://doi.org/10.3390/app112311255

    Article  MATH  Google Scholar 

  • Kaur G, Sharma A (2023) A deep learning-based model using hybrid feature extraction approach for consumer sentiment analysis. J Big Data 10(1):5

    MATH  Google Scholar 

  • Khasanah IN (2021) Sentiment classification using fasttext embedding and deep learning model. Proc Comput Sci 189:343–350

    MATH  Google Scholar 

  • Khodaverdian Z, Sadr H, Edalatpanah SA et al (2024) An energy aware resource allocation based on combination of CNN and GRU for virtual machine selection. Multimed Tools Appl 83:25769–25796. https://doi.org/10.1007/s11042-023-16488-2

    Article  MATH  Google Scholar 

  • Kırelli Y, Özdemir Ş (2021) Sentiment classification performance analysis based on glove word embedding. Sakarya Univ J Sci 25(3):639–646

    MATH  Google Scholar 

  • Li L, Goh TT, Jin D (2020) How textual quality of online reviews affect classification performance: a case of deep learning sentiment analysis. Neural Comput Appl 32:4387–4415

    MATH  Google Scholar 

  • Lin JW, Thanh TD, Chang RG (2022) Multi-channel word embeddings for sentiment analysis. Soft Comput 26(22):12703–12715

    MATH  Google Scholar 

  • Lin X, Zhang Y, Li C, Wang J, Luo P, Zhou H (2019) A new data analysis method based on feature linear combination. J Biomed Inf 94:103173

    MATH  Google Scholar 

  • Malhotra R, Singh P (2023) Recent advances in deep learning models: a systematic literature review. Multimed Tools Appl 82:44977–45060

    MATH  Google Scholar 

  • Marreddy M, Mamidi R (2023) Learning sentiment analysis with word embeddings. In: Computational intelligence applications for text and sentiment data analysis. Academic Press, pp 141–161

  • Mendon S, Dutta P, Behl A, Lessmann S (2021) A hybrid approach of machine learning and lexicons to sentiment analysis: enhanced insights from twitter data of natural disasters. Inf Syst Front 23(5):1145–1168. https://doi.org/10.1007/s10796-021-10107-x

    Article  Google Scholar 

  • Mendon S, Dutta P, Behl A, Lessmann S (2021) A hybrid approach of machine learning and lexicons to sentiment analysis: enhanced insights from twitter data of natural disasters. Inf Syst Front 23(5):1145–1168

    Google Scholar 

  • Mozetiˇc I, Grˇcar M, Smailovi´c J(2016) Multilingual Twitter sentiment classification: the role of human annotators, pp 639–646

  • Mutinda J, Mwangi W, Okeyo G (2021) Lexicon-pointed hybrid N-gram features extraction model (LeNFEM) for sentence level sentiment analysis. Eng Rep 132:3

    Google Scholar 

  • Mutinda J, Mwangi W, Okeyo G (2023) Sentiment analysis of text reviews using lexicon-enhanced Bert embedding (LeBERT) model with convolutional neural network. Appl Sci 13:1445. https://doi.org/10.3390/app13031445

    Article  Google Scholar 

  • Nandwani P, Verma R (2021) A review on sentiment analysis and emotion detection from text. Soc Netw Anal Min 11(1):81

    MATH  Google Scholar 

  • Nedjah N, Santos I, de Macedo Mourelle L (2022) Sentiment analysis using convolutional neural network via word embeddings. Evol Intell 15(4):2295–2319

    MATH  Google Scholar 

  • Paulraj D, Ezhumalai P, Prakash Mohan (2024) A deep learning modified neural network (DLMNN) based proficient sentiment analysis technique on twitter data. J Exp Theor Artif Intell 36(3):415–434

    Google Scholar 

  • Pennington J, Socher R, Manning CD (2014) Glove: global vectors for word representation. In: Proceedings of the 2014 conference on empirical methods in natural language processing (EMNLP), pp 1532–1543

  • Rakshit P, Sarkar A (2024) A supervised deep learning-based sentiment analysis by the implementation of Word2Vec and GloVe Embedding techniques. Multimed Tools Appl. https://doi.org/10.1007/s11042-024-19045-7

    Article  MATH  Google Scholar 

  • Rezaei S, Tanha J, Roshan S, Jafari Z, Molaei M, Mirzadoust S, Khoshamouz T (2024) An experimental study of sentiment classification using deep-based models with various word embedding techniques. J Exp Theor Artif Intell 1:1–37

    Google Scholar 

  • Rezaeinia SM, Rahmani R, Ghodsi A, Veisi H (2019) Sentiment analysis based on improved pre-trained word embeddings. Expert Syst Appl 117:139–147

    Google Scholar 

  • Sadr H, Salari A, Ashoobi MT et al (2024) Cardiovascular disease diagnosis: a holistic approach using the integration of machine learning and deep learning models. Eur J Med Res 29:455

    Google Scholar 

  • Saleena N (2018) An ensemble classification system for twitter sentiment analysis. Proc Comput Sci 132:937–946

    MATH  Google Scholar 

  • Samih Amina, Ghadi Abderrahim, Fennan Abdelhadi (2022) Enhanced sentiment analysis based on improved word embeddings and XGboost. Int J Electr Comput Eng 13:2

    Google Scholar 

  • Sivakumar S, Rajalakshmi R (2021) Analysis of sentiment on movie reviews using word embedding self-attentive LSTM. Int J Ambient Comput Intell 12(2):33–52

    MATH  Google Scholar 

  • Suhartono D, Purwandari K, Jeremy NH, Philip S, Arisaputra P, Parmonangan IH (2023) Deep neural networks and weighted word embeddings for sentiment analysis of drug product reviews. Proc Comput Sci 216:664–671

    Google Scholar 

  • Tan KL, Lee CP, Anbananthen KSM, Lim KM (2022) RoBERTa-LSTM: a hybrid model for sentiment analysis with transformer and recurrent neural network. IEEE Access 10:21517–21525

    Google Scholar 

  • Tomas Mikolov, Ilya Sutskever, Kai Chen, Greg S Corrado, and Jeff Dean.(2013) Distributed representations of words and phrases and their compositionality. In: Advances in neural information processing systems. 11:3111–3119

  • Wadawadagi R, Pagi V (2020) Sentiment analysis with deep neural networks: comparative study and performance assessment. Artif Intell Rev 53(8):6155–6195

    MATH  Google Scholar 

  • Wang Q, Zhang W, Lei T, Cao Y, Peng D, Wang X (2023) CLSEP: contrastive learning of sentence embedding with prompt. Knowl-Based Syst 266:110381

    MATH  Google Scholar 

  • Wankhade M, Rao ACS, Kulkarni C (2022) A survey on sentiment analysis methods, applications, and challenges. Artif Intell Rev 55:135–146. https://doi.org/10.1007/s10462-022-10144-1

    Article  MATH  Google Scholar 

  • Xiang Q, Huang T, Zhang Q, Li Y, Tolba A, Bulugu I (2023) A novel sentiment analysis method based on multi-scale deep learning. Math Biosci Eng 20(5):8766–8781

    MATH  Google Scholar 

  • Yadav A, Vishwakarma DK (2021) Sentiment analysis using deep learning architectures: a review. Artif Intell Rev 53:4335–4385

    MATH  Google Scholar 

Download references

Author information

Author notes

  1. Emna Benmohamed and Hela Ltifi have contributed equally to this work.

Authors and Affiliations

  1. REGIM-Lab.: Research Groups in Intelligent Machines, LR11ES48, Faculty of Sciences Economics and Management of Sfax, University of Sfax, 3100, Sfax, Tunisia

    Chafika Ouni

  2. Department of Computer Science, College of Engineering and Information Technology, Onaizah Colleges, 51452, Onaizah, Saudi Arabia

    Emna Benmohamed

  3. Computer Science and Mathematics Department, Faculty of Sciences and Techniques of Sidi Bouzid, University of Kairouan, 3100, Kairouan, Tunisia

    Hela Ltifi

Authors
  1. Chafika Ouni
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Emna Benmohamed
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Hela Ltifi
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

All authors contributed.

Corresponding author

Correspondence to Chafika Ouni.

Ethics declarations

Competing interests

The authors declare no competing interests.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Ouni, C., Benmohamed, E. & Ltifi, H. Sentiment analysis deep learning model based on a novel hybrid embedding method. Soc. Netw. Anal. Min. 14, 210 (2024). https://doi.org/10.1007/s13278-024-01367-x

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • DOI: https://doi.org/10.1007/s13278-024-01367-x

Keywords