Saachin Bhatt, Mustansar Ali Ghazanfar, Mohammad Hossein Amirhosseini
This research explores the impact of social media sentiments on predicting Bitcoin prices using machine learning models, integrating on-chain data, and applying a Multi Modal Fusion Model. Historical crypto market, on-chain, and Twitter data from 2014 to 2022 were used to train models including K-Nearest Neighbors, Logistic Regression, Gaussian Naive Bayes, Support Vector Machine, Extreme Gradient Boosting, and Multi Modal Fusion. Performance was compared with and without Twitter sentiment data which was analysed using the Twitter-roBERTa and VADAR models. Inclusion of sentiment data enhanced model performance, with Twitter-roBERTa-based models achieving an average accuracy score of 0.81. The best performing model was an optimised Multi Modal Fusion model using Twitter-roBERTa, with an accuracy score of 0.90. This research underscores the value of integrating social media sentiment analysis and onchain data in financial forecasting, providing a robust tool for informed decision-making in cryptocurrency trading.
Relation triple extraction (RTE) is an essential task in information extraction and knowledge graph construction. Despite recent advancements, existing methods still exhibit certain limitations. They just employ generalized pre-trained models and do not consider the specificity of RTE tasks. Moreover, existing tagging-based approaches typically decompose the RTE task into two subtasks, initially identifying subjects and subsequently identifying objects and relations. They solely focus on extracting relational triples from subject to object, neglecting that once the extraction of a subject fails, it fails in extracting all triples associated with that subject. To address these issues, we propose BitCoin, an innovative Bidirectional tagging and supervised Contrastive learning based joint relational triple extraction framework. Specifically, we design a supervised contrastive learning method that considers multiple positives per anchor rather than restricting it to just one positive. Furthermore, a penalty term is introduced to prevent excessive similarity between the subject and object. Our framework implements taggers in two directions, enabling triples extraction from subject to object and object to subject. Experimental results show that BitCoin achieves state-of-the-art results on the benchmark datasets and significantly improves the F1 score on Normal, SEO, EPO, and multiple relation extraction tasks.
Many researchers agree that sentiment analysis can improve the performance of quantitative trading models. We develop two off-the-shelf solutions for analyzing the sentiments of cryptocurrency-related social media posts. First, we posttrain and fine-tune a Twitter-oriented model based on the bidirectional encoder representations from transformers (BERT) architecture, BERTweet, on the cryptocurrency domain, resulting in CryptoBERT. Second, we generate the language-universal cryptocurrency emoji (LUKE) sentiment lexicon and prediction pipeline, utilizing the sentiment of emojis prevalent in social media. CryptoBERT is highly accurate, while LUKE is suitable for non-English posts, thus allowing for direct classification and noisy label generation in less popular languages. Our research can help cryptocurrency investors develop trading software supported by sentiments mined from social media.
Achraf Boumhidi, Abdessamad Benlahbib, El Habib Nfaoui
Reputation generation systems are decision-making tools used in different domains including e-commerce, tourism, social media events, etc. Such systems generate a numerical reputation score by analyzing and mining massive amounts of various types of user data, including textual opinions, social interactions, shared images, etc. Over the past few years, users have been sharing millions of tweets related to cryptocurrencies. Yet, no system in the literature was designed to handle the unique features of this domain with the goal of automatically generating reputation and supporting investors’ and users’ decision-making. Therefore, we propose the first financially oriented reputation system that generates a single numerical value from user-generated content on Twitter toward cryptocurrencies. The system processes the textual opinions by applying a sentiment polarity extractor based on the fine-tuned auto-regressive language model named XLNet. Also, the system proposes a technique to enhance sentiment identification by detecting sarcastic opinions through examining the contrast of sentiment between the textual content, images, and emojis. Furthermore, other features are considered, such as the popularity of the opinions based on the social network interactions (likes and shares), the intensity of the entity’s demand within the opinions, and news influence on the entity. A survey experiment has been conducted by gathering numerical scores from 827 Twitter users interested in cryptocurrencies. Each selected user assigns 3 numerical assessment scores toward three cryptocurrencies. The average of those scores is considered ground truth. The experiment results show the efficacy of our model in generating a reliable numerical reputation value compared with the ground truth, which proves that the proposed system may be applied in practice as a trusted decision-making tool.
Cryptocurrencies are digital currencies that operate on the blockchain, which is the technology that offers security and decentralization. The principal characteristic of cryptocurrencies is that they are not generally issued by a central authority. Many factors can influence the volatility of prices. This paper enables to drive insights into the behavior of markets through the application of sentiment analysis of Tweets, Google news and machine learning techniques for the challenging task of cryptocurrency price prediction. Most of the studies have focused exclusively on the sentiment analysis of tweets. In this work, we propose the use of common machine learning tools and available Google News data for predicting the price of crypto. We present the results of the Long Short-Term Memory (LSTM) model using Tweets and Google News data.
This paper predicts sentiments of crypto currency news articles using BERT (Bidirectional Encoder Representation) model, as there is a lack of research in crypto currency price prediction using natural language processing. The text data obtained is unlabeled and it is labelled using a parsimonious rule-based model and then BERT is used to dassify news sentiment as “Positive”, “Negative” or “Neutral” which may be helpful in reading cryptocurrency market movement.
The cryptocurrency ecosystem has been the centre of discussion on many social media platforms, following its noted volatility and varied opinions. Twitter is rapidly being utilised as a news source and a medium for bitcoin discussion. Our algorithm seeks to use historical prices and sentiment of tweets to forecast the price of Bitcoin. In this study, we develop an end-to-end model that can forecast the sentiment of a set of tweets (using a Bidirectional Encoder Representations from Transformers - based Neural Network Model) and forecast the price of Bitcoin (using Gated Recurrent Unit) using the predicted sentiment and other metrics like historical cryptocurrency price data, tweet volume, a user's following, and whether or not a user is verified. The sentiment prediction gave a Mean Absolute Percentage Error of 9.45%, an average of real-time data, and test data. The mean absolute percent error for the price prediction was 3.6%.
With the expansion of social networks, sentiment analysis has become one of the hot topics in machine learning. However, in traditional sentiment analysis, the text is considered of a general nature and ignores the different aspects that may exist in the text. This paper presents a hybrid model of transfer deep learning methods for the aspect-oriented sentiment analysis of influencers’ tweets to predict the trend of cryptocurrencies. In the first model, different aspects of tweets are extracted using the Concept Latent Dirichlet Allocation (Concept-LDA). Then, by using the pre-trained RoBERTa network and combining it with the Bidirectional Gated Recurrent Unit (BiGRU) deep learning network and attention layer, sentiments of different aspects of tweets are determined. In the following, the price trend of seven cryptocurrencies, Bitcoin, Ethereum, Binance, Ripple, Dogecoin, Cardano, and Solana, is determined using the historical price and the polarity of tweets with BiGRU combined deep neural network and the attention layer. Also, we used the gridsearch method to select dropout hyper-parameters, learning rate, and the number of GRU units, and the Akaike Information Criterion (AIC) criterion confirmed the results of this proposed combination. The results show that the proposed model in the aspect-based sentiment analysis section has been able to achieve 5.94% accuracy and 9.9% improvement in the f1-score on the SemEval 2015 dataset and 2.61% improvement on the SemEval 2016 dataset in f1-score compared to the state-of-arts. Also, the results of predicting the price trend of cryptocurrencies show that the proposed model has correctly recognized the price trend in the next five days in 77% of cases according to the ROC-AUC criterion.
The volume of information on the internet is currently rising dramatically. Social media platforms/e-commerce market place is producing a lot of data, including reviews, comments, and opinions, every day. As there are a number of fake reviews should incorporate Spam detection to produce a genuine opinion. Fake reviews are growing problem in online shopping, and they have a significant impact on consumer’s decision-making. Many people today base their decisions when choosing a product or service on social media opinions. Because so many false or phoney evaluations have been written by businesses or individuals for a variety of reasons, detecting opinion spam is a difficult and time-consuming task. They produce fictitious reviews to deceive users or automated detection systems by elevating or degrading the reputations of their target products in order to elevate or lower them. In this article, we’ll regulate it by leveraging blockchain technology to make the review system more authentic by allowing only legitimate product purchasers to submit evaluations using their account credentials. We use the Ethereum blockchain to authenticate user credentials, and we only permit verified users to purchase things. Also, we only permit customers to leave reviews or comments on products, ensuring that the reviews are accurate.
In the financial market, Bitcoin analytics has gained lots of attention due to its high-risk high-reward nature. It is interesting to find better techniques to analyze and predict the Bitcoin price change. In this paper, we propose Bitcoin Evolution Analytics, which aims to predict the Bitcoin price change after one hour as Bearish or Bullish. For the prediction, the approach combines the Sentiment analysis and the Technical indicators. For Sentiment analysis of tweets related to Bitcoin, the approach uses three Natural Language Processing (NLP) libraries, namely VADER, FinBERT, and TextBlob, which generated eight different sentiment scores. For Technical indicators, the approach used three features of Bitcoin: User Sentiment Score, Aroon Indicators, and Accumulation/Distribution Line Indicators. We represented all these features of Bitcoin Data over time, which created a novel Bitcoin State Series. To predict the price change of the next hour as Bearish or Bullish, we built the state series for each hour of continuous 13 months (March 2021 - March 2022). To find the most reliable set of features, we have trained 27 ML models. For each feature set, we compared the average and maximum of the accuracies and f-measures. The results of our experiment show that considering the followers of the user as the "weight" of the sentiment gives a more accurate prediction. We found that a combination of Sentiment Analysis and Technical Indicators performs better than using only Sentiment Analysis.
Isabella Donita Hasan, Raymond Sunardi Oetama, Aldo Lionel Saonard
The high public interest in cryptocurrencies is increasing over time. Cryptocurrencies are gaining worldwide attention because of their unique and unpredictable nature. Nowadays, cryptocurrencies can be used for various things, one of which is for investment. In investing in cryptocurrencies, various analyzes are needed to consider trade flows. One way to analyze it is by analyzing public sentiment which consists of positive and negative sentiments. However, there has been no previous research on the use of machine learning approaches and feature selection in sentiment analysis of Twitter tweets and retweets. The research was conducted by analyzing public sentiment using a machine learning algorithm, namely the Support Vector Machine. In addition to using the Support Vector Machine, Chi-square is also used in feature selection to help reduce noise in a sentence. Retweets will considerably improve sentiment label classification. The performance of sentiment analysis can be improved across the board by at least 91%. The sentiment analysis findings from this study are positive. This implies that a trader can take cryptocurrencies like Bitcoin, Ethereum, and Ripple into account while deciding on the type of investment.
Cryptocurrencies have emerged in recent years and have continued to grow until they have become very popular, widespread, and surrounded by various pros and cons of their innovative developments. This study uses sentiment analysis on Twitter towards cryptocurrencies to create positive and negative trends based on comments by classifying data on Twitter. The dataset used is a Tweet related to cryptocurrency in June 2022. To get positive or negative sentiment of this research using SVM classification method with the following stages. The dataset goes through the stages of preprocessing, labeling, imbalance handling, train test split, TF-IDF weighting to transform the data from text to numeric which are then used for sentiment analysis using SVM. This research resulted in sentiment analysis based on the TextBlob library to determine positive sentiment and negative sentiment. The accuracy of the application of SVM in this study is known through the use of k-fold cross validation and three methods, namely undersampling, without imbalance handling and oversampling and three comparisons of train test splits, namely 90:10, 80:20, and 70:30. In k-fold cross validation, an accuracy of 93. 19% was obtained. While the other three methods, obtained three highest accuracy where the accuracy is in a ratio of 80:20, namely 94.64% for undersampling, 93.42% for data without imbalance handling, and 93.40% for oversampling. The best accuracy is in the data that goes through the undersampling process with a ratio of 80:20 which is of 94.64% and the sentiment analysis result is a positive sentiment.
Abstract Cryptocurrency investment especially Bitcoin, has become favourable over recent years due to promising returns in the future. However, the movement of price is mainly speculation-based as these currencies are still new in the market. The COVID-19 outbreak boosted research interest in predicting the price fluctuation of Bitcoin since cryptocurrency trading produced many millionaires. Five lexicon-based Twitter sentiment analysis approaches are examined to see the effect of Tweets on the price of Bitcoin during the pre- and post- COVID-19 period. Results show that negative Twitter sentiments affected the price of Bitcoin pre- COVID-19 and the second year of post- COVID-19 when Elon Musk actively criticised Bitcoin on Twitter.
E. Padmalatha, Sailekya Sheral, K Dhanush, S. Samveeth · 6 authors
Bitcoin, as one of the most popular cryptocurrencies, is notorious for its concerning volatility on any given day, which leads to people having mixed feelings about it. This paper examines the opinions of people all over the world using data gathered from the social media platform Twitter, to decide if investing in bitcoin is a good idea for future. The opinions are analyzed and classified using the Bernoulli and Multinomial Naive Bayes model through sentiment analysis, the models implemented yielded 87 and 86 percent of accuracies respectively. Furthermore, the variation in sentiment over time is comparedto the variation in bitcoin price over the same period.
Emotions form an essential and fundamental aspect of our lives. What we do and say reflects some of our feelings in some way, though not directly. We must examine these feelings using emotional data, also known as affect data, to comprehend a person's basic behavior. Text, voice, facial expressions, and other data types can be included. Since social networking websites have become so popular, many individuals have started reading the material on these numerous sites.Twitter is one of these social networking sites. People's feelings and thoughts about a subject reveal positive, negative, and neutral emotional values. Doing sentiment analysis on Twitter is a very important and challenging task. In this study, we aim to investigate the sentiments of Bitcoin and provide an overview of its effect on the value of Bitcoin by utilizing the power of deep learning architectures and machine learning methods. The study collected tweets in English shared on Twitter between December 12, 2021, and March 13, 2022. First, people's feelings about Bitcoin were assessed using TextBlob, a natural language processing (NLP) tool. Then, it was done using basic machine learning algorithms for sentiment classification and CNN, LSTM, and BiLSTM deep learning architectures that we modeled. However, deep learning models were tested separately with the TF-IDF and Glove word embedding approaches. Experimental results prove the success of deep learning architectures using the Glove word embedding approach.
As the cryptocurrency trading market has grown significantly in recent years, the number of comments related to cryptocurrency has increased tremendously in social media platforms. Due to this, sentiment analysis of the cryptocurrency-related comments has become highly desirable to give a comprehensive picture of peoples’ opinions about the trend of the market. In this regard, we perform cryptocurrency-related text sentiment classification using tweets based on positive and negative sentiments. For increasing the efficacy of the sentiment analysis, we introduce a novel deep neural network hybrid architecture which is composed of an embedding layer, a convolution layer, a group-wise enhancement mechanism, a bidirectional layer, an attention mechanism, and a fully connected layer. Local features are derived using a convolution layer, and weight values associated with intuitive features are developed using the group-wise enhancement mechanism. After feeding the improved context vector to the bidirectional layer to grab global features, the attention mechanism and the fully connected layer have been employed. The experimental findings indicate that the proposed architecture outperforms the state-of-the-art architectures with an accuracy value of 93.77%.
Individual mental feelings and reactions are getting more significant as they help researchers, domain experts, businesses, companies, and other individuals understand the overall response of every individual in specific situations or circumstances. Every pure and compound sentiment can be classified using a dataset, which can be in the form of Twitter text by various Twitter users. Twitter is one of the vital platforms for individuals to participate and share their ideas about different topics; it is also considered to be one of the most famous and the biggest website for micro-blogging on the Internet. One of the key purposes of this study is to classify pure and compound sentiments based on text related to cryptocurrencies, an innovative way of trading and flourishing daily. The cryptocurrency market incurs many fluctuations in the coins’ value. A small positive or negative piece of news can sensate the whole scenario about the specific cryptocurrencies. In this paper, individuals’ pure and compound sentiments based on cryptocurrency-related Twitter text are classified. The dataset is collected through the Twitter API. In WEKA, the two deployment schemes are compared; firstly, straight with single feature selection technique (Tweet to lexicon feature vector), and secondly, a tetrad of feature selection techniques (Tweet to lexicon feature vector, Tweet to input lexicon feature vector, Tweet to SentiStrength feature vector, and Tweet to embedding feature vector) are used to purify the data LibLINEAR (LL) classifier, which contains fast algorithms for linear classification using L2-regularization L2-loss support vector machines (Dual SVM). The LL classifier differs in that it can potentially alleviate the sum of the absolute values of errors rather than the sum of the squared errors and is typically much speedier. Based on the overall performance parameters, the deployment scheme containing the tetrad of feature selection techniques with the LL classifier is considered the best choice for the purpose of classification. Among machine learning techniques, LL produces effective results and gives an efficient performance compared to other prevailing techniques. The findings of this research would be beneficial for Twitter users as well as cryptocurrency traders.
Traditional sentiment analysis methods are based on text-, visual- or audio-processing using different machine learning and/or deep learning architecture, depending on the data type. This situation comes with technical processing diversity and cultural temperament effect on analysis of the results, which means the results can change according to the cultural diversities. This study integrates a blockchain layer with an LSTM architecture. This approach can be regarded as a machine learning application that enables the transfer of the metadata of the ledger to the learning database by establishing a cryptographic connection, which is created by adding the next sentiment with the same value to the ledger as a smart contract. Thus, a "Proof of Learning" consensus blockchain layer integrity framework, which constitutes the confirmation mechanism of the machine learning process and handles data management, is provided. The proposed method is applied to a Twitter dataset with the emotions of negative, neutral and positive. Previous sentiment analysis methods on the same data achieved accuracy rates of 14% in a specific culture and 63% in a the culture that has appealed to a wider audience in the past. This study puts forth a very promising improvement by increasing the accuracy to 92.85%.
Virtual currencies or cryptocurrencies are based on Blockchain technology, also known as distributed ledger technology. As of March 2022, there are already over 10k virtual coins, their number being continuously growing since 2013. This paper aims to extract the public sentiment expressed towards the cryptocurrency market and Blockchain technology, two topics widely debated in the last decade. Our research was based on the use of Twitter data, collected with the help of an API in the RStudio environment.