Social Network Sentiment Analysis Using Hybrid Deep Learning Models
Source abstract
Abstract
The exponential growth in information on the Internet, particularly within social networks, highlights the importance of sentiment and opinion analysis. The intrinsic characteristics of the Spanish language coupled with the short length and lack of context of messages on social media pose a challenge for sentiment analysis in social networks. In this study, we present a hybrid deep learning model combining convolutional and long short-term memory layers to detect polarity levels in Twitter for the Spanish language. Our model significantly improved the accuracy of existing approaches by up to 20%, achieving accuracies of around 76% for three polarities (positive, negative, neutral) and 91% for two polarities (positive, negative).
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Sentiment Analysis and Opinion Mining · Advanced Text Analysis Techniques · Misinformation and Its Impacts
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Escuela Técnica Superior de Ingenieros de Telecomunicación, Universidad de Valladolid, 47005 Valladolid, Spain
Escuela de Ingeniería Informática, Universidad de Valladolid, 47005 Valladolid, Spain
Funding
University of Valladolid
References (47)
Show source-provided references
1. Kemp, S. (2022). Digital 2022: Global Overview Report, Kepios Pte. Ltd.. Available online: https://datareportal.com/reports/digital-2022-global-overview-report.
2. The evolution of sentiment analysis—A review of research topics, venues, and top cited papers10.1016/j.cosrev.2017.10.002 ↗
3. Sentiment analysis in Twitter10.1017/S1351324912000332 ↗
4. Cervantes, I. (2021). El Español en el Mundo 2021. Anuario del Instituto Cervantes, El español en el Mundo, Instituto Cervantes. Available online: https://cvc.cervantes.es/lengua/anuario/anuario_21/.
5. Perez-Rosas, V., Banea, C., and Mihalcea, R. (2012, January 23–25). Learning Sentiment Lexicons in Spanish. Proceedings of the Eight International Conference on Language Resources and Evaluation (LREC’12), Istanbul, Turkey.
6. Betancourt, E.R., Chacón, P.S., and Murillo, E.C. (October, January 30). Deep Neural Network Comparison for Spanish Tweets Polarity Classification. Proceedings of the 2019 XLV Latin American Computing Conference (CLEI), Panama, Panama.10.1109/CLEI47609.2019.235083 ↗
7. Comparative Analysis of Lexicon and Machine Learning Approach for Sentiment Analysis
8. Köhn, A. (2015, January 19–21). What is in an Embedding? Analyzing Word Embeddings through Multilingual Evaluation. Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, Lisbon, Portugal.10.18653/v1/D15-1246 ↗
9. TASS 2018: The Strength of Deep Learning in Language Understanding Tasks
10. SEPLN (2023, October 06). TASS: Workshop on Semantic Analysis at SEPLN. Available online: http://tass.sepln.org/2020/.
11. Semantic orientation for polarity classification in Spanish reviews10.1016/j.eswa.2013.06.076 ↗
12. Hu, M., and Liu, B. (2004, January 22–25). Mining and Summarizing Customer Reviews. Proceedings of the KDD ’04: Tenth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Seattlem WA, USA.10.1145/1014052.1014073 ↗
13. The Spanish adaptation of ANEW (Affective Norms for English Words)10.3758/BF03193031 ↗
14. Building layered, multilingual sentiment lexicons at synset and lemma levels10.1016/j.eswa.2014.04.005 ↗
15. Lexicon-based sentiment analysis of Twitter messages in Spanish
16. Batyrshin, I., and González Mendoza, M. Empirical Study of Machine Learning Based Approach for Opinion Mining in Tweets. Proceedings of the Advances in Artificial Intelligence.
17. Brooke, J., Tofiloski, M., and Taboada, M. (2009, January 14–16). Cross-linguistic sentiment analysis: From English to Spanish. Proceedings of the International Conference RANLP-2009, Borovets, Bulgaria.
18. Lexicon-Based Methods for Sentiment Analysis10.1162/COLI_a_00049 ↗
19. On the usefulness of lexical and syntactic processing in polarity classification of Twitter messages10.1002/asi.23284 ↗
20. Combining resources to improve unsupervised sentiment analysis at aspect-level10.1177/0165551515593686 ↗
21. Studying the Scope of Negation for Spanish Sentiment Analysis on Twitter10.1109/TAFFC.2017.2693968 ↗
22. Opinion mining based on the Spanish adaptation of ANEW on opinions about hotels
23. Amores, M., Arco, L., and Barrera, A. (2016, January 11–15). Efectos de la negación, modificadores, jergas, abreviaturas y emoticonos en el análisis de sentimiento. Proceedings of the IWSW, Montréal, QB, Canada.
24. Sentiment analysis and topic detection of Spanish tweets: A comparative study of of NLP techniques
25. Gamallo, P., Garcia, M., and Fernández-Lanza, S. (2013, January 20). TASS: A Naive-Bayes strategy for sentiment analysis on Spanish tweets. Proceedings of the Workshop on Sentiment Analysis at Sepln (TASS2013), Madrid, Spain.10.3115/v1/S14-2026 ↗
26. Montenegro, O., Pabón, O.S., and Gutiérrez De Piñerez R., R.E. (, January 25–29). A Deep Learning Approach for Negation Detection from Product Reviews written in Spanish. Proceedings of the 2021 XLVII Latin American Computing Conference (CLEI), Cartago, Costa Rica.10.1109/CLEI53233.2021.9640190 ↗
27. Myska, V., Burget, R., Povoda, L., and Dutta, M.K. (2019, January 1–3). Linguistically independent sentiment analysis using convolutional-recurrent neural networks model. Proceedings of the 2019 42nd International Conference on Telecommunications and Signal Processing (TSP), Budapest, Hungary.10.1109/TSP.2019.8768887 ↗
28. Cerón-Guzmán, J.A., and León-Guzmán, E. (2016, January 8–10). A sentiment analysis system of Spanish tweets and its application in Colombia 2014 presidential election. Proceedings of the 2016 IEEE International Conferences on Big Data and Cloud Computing (BDCloud), Social Computing and Networking (Socialcom), Sustainable Computing and Communications (Sustaincom) (BDCloud-Socialcom-Sustaincom), Atlanta, GA, USA.10.1109/BDCloud-SocialCom-SustainCom.2016.47 ↗
29. Chollet, F. (2021). Deep Learning with Python, Manning Publications Co.
30. Automatic classification of sexism in social networks: An empirical study on twitter data10.1109/ACCESS.2020.3042604 ↗
31. A multi-task learning approach to hate speech detection leveraging sentiment analysis10.1109/ACCESS.2021.3103697 ↗
32. Urpay-Camasi, J., Garcia-Calderon, J., and Shiguihara, P. (2021, January 17–19). A Method to Construct Guidelines for Spanish Comments Annotation for Sentiment Analysis. Proceedings of the 2021 IEEE Sciences and Humanities International Research Conference (SHIRCON), Lima, Peru.10.1109/SHIRCON53068.2021.9652313 ↗
33. Chiruzzo, L., and Rosá, A. (2018, January 18). RETUYT-InCo at TASS 2018: Sentiment Analysis in Spanish Variants using Neural Networks and SVM. Proceedings of the TASS@ SEPLN, Sevilla, Spain.
34. Pastorini, M., Pereira, M., Zeballos, N., Chiruzzo, L., Rosá, A., and Etcheverry, M. (2019, January 24). RETUYT-InCo at TASS 2019: Sentiment Analysis in Spanish Tweets. Proceedings of the IberLEF@ SEPLN, Bilbao, Spain.
35. González, J.Á., and Lluís-F. Hurtado, F.P. (2018, January 18). ELiRF-UPV at TASS 2018: Sentiment Analysis in Twitterbased on Deep Learning. Proceedings of the TASS 2018: Workshop on Semantic Analysis at SEPLN, Sevilla, Spain.
36. Pla, F., and Hurtado, L.F. (2014, January 18–20). Sentiment analysis in Twitter for Spanish. Proceedings of the Natural Language Processing and Information Systems: 19th International Conference on Applications of Natural Language to Information Systems, NLDB 2014, Montpellier, France.10.1007/978-3-319-07983-7_27 ↗
37. An Efficient Hybrid Approach for Twitter Sentiment Analysis based on Bidirectional Recurrent Neural Networks
38. Emotion analysis model of microblog comment text based on CNN-BiLSTM
39. SA-ASBA: A hybrid model for aspect-based sentiment analysis using synthetic attention in pre-trained language BERT model with extreme gradient boosting10.1007/s11227-022-04881-x ↗
40. Shah, S., Ghomeshi, H., Vakaj, E., Cooper, E., and Mohammad, R. (2023). An Ensemble-Learning-Based Technique for Bimodal Sentiment Analysis. Big Data Cogn. Comput., 7.10.20944/preprints202303.0460.v1 ↗
41. Witten, I.H., Frank, E., and Hell, M.A. (2011). Data Mining, Morgan Kaufmann. [3rd ed.].
42. Chollet, F., and Keras Team (2022, April 20). Keras. Available online: https://github.com/fchollet/keras-resources.
43. Team, G.B. (2023, October 06). TensorFlow Library. Available online: https://keras.io/.
44. SEPLN 2022 (2023, October 06). Sociedad Española para el Procesamiento del Lenguaje Natural, A Coruña, Spain, 20–23 September 2022. Available online: https://sepln2022.grupolys.org/.
45. Bird, S., Klein, E., Looper, E., and NKLT-Natural Language Processing Library (2023, October 06). Natural Language Toolkit Project. Available online: https://www.nltk.org.
46. Developers, S., and Snowball Algorithms for Stemming (2023, October 06). Python Package Index. Available online: https://snowballstem.org/.
47. Larose, D.T., and Larose, C.D. (2014). Discovering Knowledge in Data: An Introduction to Data Mining, John Wiley & Sons.10.1002/9781118874059 ↗