Deep learning-based sentiment classification in Amharic using multi-lingual datasets

Tesfagergish, Senait Gebremichael; Damasevicius, Robertas; Kapociūtė-Dzikienė, Jurgita

doi:10.2298/csis230115042t

Cited by 5 publications

(1 citation statement)

References 53 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The lack of public data sets, particularly for pragmatic studies, is one of the largest hurdles to the analysis of hybrid languages such as Hinglish [15,16]. It is difficult to construct accurate algorithms for sentiment and pragmatic analysis in the absence of appropriate data such as for low-resourced language [17]. Beside this, the complexity of Hinglish, which mixes two distinct grammatical systems and vocabularies, makes it challenging to develop suitable models for machine learning techniques [13].…”

Section: Introductionmentioning

confidence: 99%

Multimodal Hinglish Tweet Dataset for Deep Pragmatic Analysis

Pratibha,

Kaur,

Khurana

et al. 2024

Data

View full text Add to dashboard Cite

Wars, conflicts, and peace efforts have become inherent characteristics of regions, and understanding the prevailing sentiments related to these issues is crucial for finding long-lasting solutions. Twitter/`X’, with its vast user base and real-time nature, provides a valuable source to assess the raw emotions and opinions of people regarding war, conflict, and peace. This paper focuses on collecting and curating hinglish tweets specifically related to wars, conflicts, and associated taxonomy. The creation of said dataset addresses the existing gap in contemporary literature, which lacks comprehensive datasets capturing the emotions and sentiments expressed by individuals regarding wars, conflicts, and peace efforts. This dataset holds significant value and application in deep pragmatic analysis as it enables future researchers to identify the flow of sentiments, analyze the information architecture surrounding war, conflict, and peace effects, and delve into the associated psychology in this context. To ensure the dataset’s quality and relevance, a meticulous selection process was employed, resulting in the inclusion of explanable 500 carefully chosen search filters. The dataset currently has 10,040 tweets that have been validated with the help of human expert to make sure they are correct and accurate.

show abstract

Section: Introductionmentioning

confidence: 99%

Multimodal Hinglish Tweet Dataset for Deep Pragmatic Analysis

Pratibha,

Kaur,

Khurana

et al. 2024

Data

View full text Add to dashboard Cite

show abstract

Public opinion mining in social media about Ethiopian broadcasts using deep learning

Yibeyin,

Tehone,

Liyih

et al. 2024

Sci Rep

View full text Add to dashboard Cite

Now adays people express and share their opinions on various events on the internet thanks to social media. Opinion mining is the process of interpreting user-generated opinion data on social media. Aside from its lack of resources in opinion-mining tasks, Amharic presents numerous difficulties because of its complex structure and variety of dialects. Analyzing every comment written in Amharic is a challenging task. Significant advancements in opinion mining have been achieved using deep learning. An opinion-mining model was used in this study to classify user comments written in Amharic as positive or negative. The domains that we focus on in this study are YouTube and Facebook. From the Ethiopian broadcasts YouTube and Facebook official pages, we gathered 11,872 unstructured data for this study using www.exportcomment.com , and Facebook page tools. Text preprocessing and feature extraction techniques were used, in addition to manual annotation by linguistic specialists. The dataset was prepared for the experiment after annotation, preprocessing, and representation. LSTM, GRU, BiGRU, BiLSTM, and a hybrid of CNN with BiLSTM classifiers from the TensorFlow Keras deep learning library were used to train the model using the dataset, which was split using the 80/20 train-test method, which proved effective for classification problems. Finally, we achieved of 94.27%, 95.20%, 95.49%, 95.62%, and 96.08% using GRU, BiGRU, LSTM, BiLSTM, and CNN with BiLSTM, respectively, in word2vec embedding model.

show abstract

Sentiment Analysis in Low-Resource Settings: A Comprehensive Review of Approaches, Languages, and Data Sources

Aliyu,

Sarlan,

Usman Danyaro

et al. 2024

IEEE Access

View full text Add to dashboard Cite

The field of low-resource sentiment analysis has seen significant developments in recent years. This research review SLR evaluates the approaches and data sources utilized in low-resource sentiment analysis by deep learning. The primary aim is to discover suitable approaches for future sentiment analysis in low-resource. Our studies explore various languages, models, and data sources expressing a desire to create effective approaches. Our emphasis lies in the critical evaluation of the approaches and the datasets utilized, to identify areas where further research is needed. Our analysis study adds to the existing body of literature reviews, encompassing multilingual low-resource sentiment analysis research spanning from 2018 to 2023. The findings indicate that the transfer learning approach is the most frequently used, followed by word embedding learning and machine translation systems. Additionally, the study shows that social media is the most used platform for data collection, followed by product reviews, movies, and hotels. There has been a significant surge in the adoption of pre-trained transformers, indicating a growing interest in exploring the potential of these models for low-resource languages within the natural language processing (NLP) community. This trend is largely attributed to the novel nature of these models and their feature of being nonlabour intensive. However, the scarcity of annotated datasets for such languages remains a major hurdle. finally, these research findings are relevant and informative for any researcher working in the field of lowresource multilingual sentiment analysis. The study introduces a conceptual framework for performing sentiment analysis in low-resource. The study provides a valuable resource for future researchers.

show abstract

Deep learning-based sentiment classification in Amharic using multi-lingual datasets

Cited by 5 publications

References 53 publications

Multimodal Hinglish Tweet Dataset for Deep Pragmatic Analysis

Multimodal Hinglish Tweet Dataset for Deep Pragmatic Analysis

Public opinion mining in social media about Ethiopian broadcasts using deep learning

Sentiment Analysis in Low-Resource Settings: A Comprehensive Review of Approaches, Languages, and Data Sources

Contact Info

Product

Resources

About