Get our free extension to see links to code for papers anywhere online!

Chrome logo  Add to Chrome

Firefox logo Add to Firefox

"Sentiment Analysis": models, code, and papers

SemEval-2016 Task 4: Sentiment Analysis in Twitter

Dec 03, 2019
Preslav Nakov, Alan Ritter, Sara Rosenthal, Fabrizio Sebastiani, Veselin Stoyanov

This paper discusses the fourth year of the ``Sentiment Analysis in Twitter Task''. SemEval-2016 Task 4 comprises five subtasks, three of which represent a significant departure from previous editions. The first two subtasks are reruns from prior years and ask to predict the overall sentiment, and the sentiment towards a topic in a tweet. The three new subtasks focus on two variants of the basic ``sentiment classification in Twitter'' task. The first variant adopts a five-point scale, which confers an ordinal character to the classification task. The second variant focuses on the correct estimation of the prevalence of each class of interest, a task which has been called quantification in the supervised learning literature. The task continues to be very popular, attracting a total of 43 teams.

* SemEval-2016 
* Sentiment analysis, sentiment towards a topic, quantification, microblog sentiment analysis; Twitter opinion mining. arXiv admin note: text overlap with arXiv:1912.00741 

NLP-CIC at SemEval-2020 Task 9: Analysing sentiment in code-switching language using a simple deep-learning classifier

Sep 07, 2020
Jason Angel, Segun Taofeek Aroyehun, Antonio Tamayo, Alexander Gelbukh

Code-switching is a phenomenon in which two or more languages are used in the same message. Nowadays, it is quite common to find messages with languages mixed in social media. This phenomenon presents a challenge for sentiment analysis. In this paper, we use a standard convolutional neural network model to predict the sentiment of tweets in a blend of Spanish and English languages. Our simple approach achieved a F1-score of 0.71 on test set on the competition. We analyze our best model capabilities and perform error analysis to expose important difficulties for classifying sentiment in a code-switching setting.

* Accepted at SemEval-2020, COLING 

Social Media Sentiment Analysis for Cryptocurrency Market Prediction

Apr 19, 2022
Ali Raheman, Anton Kolonin, Igors Fridkins, Ikram Ansari, Mukul Vishwas

In this paper, we explore the usability of different natural language processing models for the sentiment analysis of social media applied to financial market prediction, using the cryptocurrency domain as a reference. We study how the different sentiment metrics are correlated with the price movements of Bitcoin. For this purpose, we explore different methods to calculate the sentiment metrics from a text finding most of them not very accurate for this prediction task. We find that one of the models outperforms more than 20 other public ones and makes it possible to fine-tune it efficiently given its interpretable nature. Thus we confirm that interpretable artificial intelligence and natural language processing methods might be more valuable practically than non-explainable and non-interpretable ones. In the end, we analyse potential causal connections between the different sentiment metrics and the price movements.

* 10 pages, 3 figures, submitted to Interpretable Natural Language Processing Workshop of AGI-2022 Conference 

Hybrid Improved Document-level Embedding (HIDE)

Jun 01, 2020
Satanik Mitra, Mamata Jenamani

In recent times, word embeddings are taking a significant role in sentiment analysis. As the generation of word embeddings needs huge corpora, many applications use pretrained embeddings. In spite of the success, word embeddings suffers from certain drawbacks such as it does not capture sentiment information of a word, contextual information in terms of parts of speech tags and domain-specific information. In this work we propose HIDE a Hybrid Improved Document level Embedding which incorporates domain information, parts of speech information and sentiment information into existing word embeddings such as GloVe and Word2Vec. It combine improved word embeddings into document level embeddings. Further, Latent Semantic Analysis (LSA) has been used to represent documents as a vectors. HIDE is generated, combining LSA and document level embeddings, which is computed from improved word embeddings. We test HIDE with six different datasets and shown considerable improvement over the accuracy of existing pretrained word vectors such as GloVe and Word2Vec. We further compare our work with two existing document level sentiment analysis approaches. HIDE performs better than existing systems.


Improving BERT Performance for Aspect-Based Sentiment Analysis

Oct 22, 2020
Akbar Karimi, Leonardo Rossi, Andrea Prati

Aspect-Based Sentiment Analysis (ABSA) studies the consumer opinion on the market products. It involves examining the type of sentiments as well as sentiment targets expressed in product reviews. Analyzing the language used in a review is a difficult task that requires a deep understanding of the language. In recent years, deep language models, such as BERT \cite{devlin2019bert}, have shown great progress in this regard. In this work, we propose two simple modules called Parallel Aggregation and Hierarchical Aggregation to be utilized on top of BERT for two main ABSA tasks namely Aspect Extraction (AE) and Aspect Sentiment Classification (ASC) in order to improve the model's performance. We show that applying the proposed models eliminates the need for further training of the BERT model. The source code is available on the Web for further research and reproduction of the results.


SOC: hunting the underground inside story of the ethereum Social-network Opinion and Comment

Nov 27, 2018
TonTon Hsien-De Huang, Po-Wei Hong, Ying-Tse Lee, Yi-Lun Wang, Chi-Leong Lok, Hung-Yu Kao

The cryptocurrency is attracting more and more attention because of the blockchain technology. Ethereum is gaining a significant popularity in blockchain community, mainly due to the fact that it is designed in a way that enables developers to write smart contracts and decentralized applications (Dapps). There are many kinds of cryptocurrency information on the social network. The risks and fraud problems behind it have pushed many countries including the United States, South Korea, and China to make warnings and set up corresponding regulations. However, the security of Ethereum smart contracts has not gained much attention. Through the Deep Learning approach, we propose a method of sentiment analysis for Ethereum's community comments. In this research, we first collected the users' cryptocurrency comments from the social network and then fed to our LSTM + CNN model for training. Then we made prediction through sentiment analysis. With our research result, we have demonstrated that both the precision and the recall of sentiment analysis can achieve 0.80+. More importantly, we deploy our sentiment analysis1 on RatingToken and Coin Master (mobile application of Cheetah Mobile Blockchain Security Center23). We can effectively provide detail information to resolve the risks of being fake and fraud problems.

* Draft 

Combination of Domain Knowledge and Deep Learning for Sentiment Analysis

Jun 26, 2018
Khuong Vo, Dang Pham, Mao Nguyen, Trung Mai, Tho Quan

The emerging technique of deep learning has been widely applied in many different areas. However, when adopted in a certain specific domain, this technique should be combined with domain knowledge to improve efficiency and accuracy. In particular, when analyzing the applications of deep learning in sentiment analysis, we found that the current approaches are suffering from the following drawbacks: (i) the existing works have not paid much attention to the importance of different types of sentiment terms, which is an important concept in this area; and (ii) the loss function currently employed does not well reflect the degree of error of sentiment misclassification. To overcome such problem, we propose to combine domain knowledge with deep learning. Our proposal includes using sentiment scores, learnt by regression, to augment training data; and introducing penalty matrix for enhancing the loss function of cross entropy. When experimented, we achieved a significant improvement in classification results.

* Accepted to MIWAI 2017 

Multiple Instance Learning Networks for Fine-Grained Sentiment Analysis

Jan 26, 2018
Stefanos Angelidis, Mirella Lapata

We consider the task of fine-grained sentiment analysis from the perspective of multiple instance learning (MIL). Our neural model is trained on document sentiment labels, and learns to predict the sentiment of text segments, i.e. sentences or elementary discourse units (EDUs), without segment-level supervision. We introduce an attention-based polarity scoring method for identifying positive and negative text snippets and a new dataset which we call SPOT (as shorthand for Segment-level POlariTy annotations) for evaluating MIL-style sentiment models like ours. Experimental results demonstrate superior performance against multiple baselines, whereas a judgement elicitation study shows that EDU-level opinion extraction produces more informative summaries than sentence-based alternatives.

* Transactions of the Association for Computational Linguistics (TACL), 2018, Volume 6, pages 17-31 
* Final published version. Please cite using appropriate date (2018). Link to journal: 

Aspect Sentiment Classification with Aspect-Specific Opinion Spans

Oct 06, 2020
Lu Xu, Lidong Bing, Wei Lu, Fei Huang

Aspect based sentiment analysis, predicting sentiment polarity of given aspects, has drawn extensive attention. Previous attention-based models emphasize using aspect semantics to help extract opinion features for classification. However, these works are either not able to capture opinion spans as a whole, or not able to capture variable-length opinion spans. In this paper, we present a neat and effective structured attention model by aggregating multiple linear-chain CRFs. Such a design allows the model to extract aspect-specific opinion spans and then evaluate sentiment polarity by exploiting the extracted opinion features. The experimental results on four datasets demonstrate the effectiveness of the proposed model, and our analysis demonstrates that our model can capture aspect-specific opinion spans.

* EMNLP 2020 

Eliminating Sentiment Bias for Aspect-Level Sentiment Classification with Unsupervised Opinion Extraction

Sep 07, 2021
Bo Wang, Tao Shen, Guodong Long, Tianyi Zhou, Yi Chang

Aspect-level sentiment classification (ALSC) aims at identifying the sentiment polarity of a specified aspect in a sentence. ALSC is a practical setting in aspect-based sentiment analysis due to no opinion term labeling needed, but it fails to interpret why a sentiment polarity is derived for the aspect. To address this problem, recent works fine-tune pre-trained Transformer encoders for ALSC to extract an aspect-centric dependency tree that can locate the opinion words. However, the induced opinion words only provide an intuitive cue far below human-level interpretability. Besides, the pre-trained encoder tends to internalize an aspect's intrinsic sentiment, causing sentiment bias and thus affecting model performance. In this paper, we propose a span-based anti-bias aspect representation learning framework. It first eliminates the sentiment bias in the aspect embedding by adversarial learning against aspects' prior sentiment. Then, it aligns the distilled opinion candidates with the aspect by span-based dependency modeling to highlight the interpretable opinion terms. Our method achieves new state-of-the-art performance on five benchmarks, with the capability of unsupervised opinion extraction.

* 11 pages, Findings of EMNLP'2021, 7th-11th November 2021