Analysis of Twitter Sentiment to Predict Financial Trends

The rapid growth of social media has rendered opinion and sentiment mining an important area of research with a wide range of applications. We focus on the Greek language and the microblogging platform Twitter, investigating methods for extracting sentiment of individual tweets as well population sentiment for different subjects (hashtags). The proposed methods are based on a sentiment lexicon. We compare several approaches for measuring the intensity of Anger, Disgust, Fear, Happiness, Sadness, and Surprise. To evaluate the effectiveness of our methods, we develop a benchmark dataset of tweets, manually rated by two humans. Our automated sentiment results seem promising and correlate to real user sentiment. Finally, we examine the variation of sentiment intensity over time for selected hashtags, and associate it with real-world events.

In this article, the authors examine the cross-sectional relationships between 325 IPOs’ first-day returns and their corresponding tweet sentiment, as defined by iSENTIUM LLC’s sentiment engine over the period from 2013 through 2014. They find that tweet sentiment is positively correlated to contemporaneous IPO returns. Interestingly enough, the authors document a positive relationship between prior days’ (1 day, 2 days, and 3 days) tweet sentiment and next-day IPO returns from offering price to opening price, along with a negative relationship between prior days’ (1 day, 2 days and 3 days) tweet sentiment and next-day IPO returns from opening price to closing price. Nevertheless, their examination of the relationship between intraday tweet sentiment and intraday IPO returns yields insignificant results. They find that tweet sentiment matters for IPO first-day performances, but the nature of this relationship appears very complex.

The advent of blogging more and more content is published on the web. Micro blogging is used to convey ideas using short text messages; video links or images .micro blogging platforms allow the public to convey their ideas through new technologies and to convey ideas and news in precise manner. This paper aims to use to text mining algorithm, which is used for gathering relevant information from passages of text, to derive a context through which predictive analysis can be made. The goal will be to use this technique to provide a predictive analysis on the electoral polls using tweets from the micro-blogging platform twitter.

In this article, we analyze the structure and content of the political conversations that took place through the microblogging platform Twitter in the context of the 2011 Spanish legislative elections and the 2012 U.S. presidential elections. Using a unique database of nearly 70 million tweets collected during both election campaigns, we find that Twitter replicates most of the existing inequalities in public political exchanges. Twitter users who write about politics tend to be male, to live in urban areas, and to have extreme ideological preferences. Our results have important implications for future research on the relationship between social media and politics, since they highlight the need to correct for potential biases derived from these sources of inequality.

The Internet as a Global/Local Site of Contestation: The Case of Iran

Big Data explosion is a phenomenon of the 21st century. Nowadays, more and more people are using the internet and creating new data regarding ideas, opinions, feelings or their views on a variety of topics and products. The micro-blogging platform Twitter is very popular and produces massive amount of data every fraction of a second and useful information may be generated from them. Sentiment analysis or opinion mining plays a major role in discovering all this information by analyzing these data and gain better insight of the public opinion on any subject in specific. In this paper a framework is proposed, built on top of the Hadoop ecosystem, for analyzing data from Twitter using a domain-specific Lexicon (in Greek).

Hybrid approach for detection of malicious profiles in twitter

This paper questions how vertical tickers on leading social media platforms (blogs, Facebook, and in particular the Twitter micro-blogging platform) pose new challenges to research that focuses on political communications campaigns. Vertical looped tickers highlight the fleeting nature of contemporary networked and socially mediated communications, since they provide an intensely compressed space (interface) and time to have posts viewed by friends and followers. This article draws upon a research collaboration with the news division of the Canadian Broadcasting Corporation (CBC) to understand how Canadian political parties increasingly worked to strategically intervene, in real time on Twitter, during a broadcast political debate.

Twitter, as the heart of publicly accessible Social Media, is one of the currently used platforms to share financial information and is a valuable source of information for different roles in the financial market. For all these roles, the quality analysis of Twitter as a source of financial information is essential to take decisions. The work in this paper is aligned with the ongoing work of the authors to a solution for irregularity monitoring in the financial market by harnessing data in online social media. To do so, the permeability of a variety of social media data feeders to financial irregularities should be analysed. That is the case of the experiment in this paper by putting the focus on Twitter microblogging platform and checking if this general purpose social media is permeable to a specific financial event. For this, we detail the analysis of Twitter permeability to a specific event in the past few months: the announcement about the merge of Tesco and Booker to create a UK’s Leading Food Business on the 27th January 2017. Both companies Tesco PLC and Booking Group PLC are listed in the main market of LSE (London Stock Exchange). Our findings provide promising evidences to address the problem of real-time detection of irregularities in the financial market via Twitter according to the volume (as a sign of the importance of the irregularity) and to other features (as signs of the potential origin causing the irregularity).

In this article, we perform sentiment analyses of Twitter location data. We use two case studies: US presidential elections of 2016 and UK general elections of 2017. For US elections, we plot state-wise user sentiment towards Hillary Clinton and Donald Trump. For UK elections, we download two disparate datasets, using keywords and location coordinates, looking for similar tendencies in sentiment towards political candidates and parties. The overall objective of the two case studies is to evaluate similarity between sentiment of location-based tweets and on-ground public opinion reflected in election results. We discover Twitter location sentiment does indeed corroborate with the election result in both cases. We also discover similar tendencies in Twitter sentiment towards political candidates and parties regardless of the methodology adopted for data collection.

Scientists aim to accurately simulate and characterize complex natural phenomena, thus revealing the underlying natural laws or physical mechanisms governing these phenomena. Conventional physical experiments require significant time and cost, and numerical methods offer an alternative solution. However, modeling complex phenomena such as fluid flow in dam‐break flood often demand extensive computational resources, which makes it impractical to perform accurate modeling the process of large‐scale dam‐break flood. This paper proposes a general knowledge‐data dually driven paradigm that enables accurate numerical modeling of complex natural phenomena without relying on large‐scale simulation data. The essential idea behind the proposed paradigm is to learn correlations between computational scale and performance by training small‐scale simulation data, thus achieving accurate modeling of large–scale complex phenomena. The steps of the proposed paradigm include (1) generating training data for small‐scale natural phenomena by integrating domain knowledge using numerical methods, (2) learning correlations between computational scale and performance using deep learning models, and (3) accurately modeling the processes of large–scale complex phenomena through resolution upscaling. We demonstrate the proposed paradigm using the case study of dam‐break flood processes and propose the smoothed particle hydrodynamics‐physics‐informed neural network (SPH‐PINN) method for accurate fine‐particle simulation of large‐scale dam‐break flood. Experimental results demonstrate that the proposed knowledge‐data dually driven paradigm provides an effective reference for accurately modeling and understanding complex natural phenomena. The proposed paradigm contributes to deeply analyzing and understanding the underlying laws and mechanisms of natural phenomena, offering valuable insights and guidance for scientific research and engineering applications.

The use of industrial byproducts in concrete applications is a scientific area of great interest over the past several years, and steel slags are acknowledged as having great potential for such use; however, the utilization rates are relatively low. The main barriers identified for this occurrence are failure to quantify benefits in terms of quality of the final product, environmental benefits, as well as cost reduction. The present research attempts to quantify these aspects for five different concrete applications examined as case studies. Laboratory-produced alternative concrete mixtures with steel slags are compared with ordinary reference concrete mixtures for their performance regarding mechanical characteristics and durability, environmental benefits using life cycle assessment, and cost estimation. The results show that there is great potential for the use of steel slag in concrete, but the benefits need to be determined for each specific use, since the values observed vary greatly depending on the application. Industrial pavement and heavyweight concretes seem to be the most favorable applications for steel slag, while the shotcrete and repair mortars examined benefited less from the use of slag.

Modeling and simulation of compressed air storage in caverns: A case study of the Huntorf plant

Accurate and reliable suspended sediment load (SSL) prediction models are necessary for planning and management of water resource structures. More recently, soft computing techniques have been used in hydrological and environmental modeling. The present paper compared the accuracy of three different soft computing methods, namely, artificial neural networks (ANNs), adaptive neuro-fuzzy inference system (ANFIS), coupled wavelet and neural network (WANN), and conventional sediment rating curve (SRC) approaches for estimating the daily SSL in two gauging stations in the USA. The performances of these models were measured by the coefficient of correlation (R), Nash-Sutcliffe efficiency coefficient (CE), root-mean-square error (RMSE), and mean absolute percentage error (MAPE) to choose the best fit model. Obtained results demonstrated that applied soft computing models were in good agreement with the observed SSL values, while they depicted better results than the conventional SRC method. The comparison of estimation accuracies of various models illustrated that the WANN was the most accurate model in SSL estimation in comparison to other models. For example, in Flathead River station, the determination coefficient was 0.91 for the best WANN model, while it was 0.65, 0.75, and 0.481 for the best ANN, ANFIS, and SRC models, and also in the Santa Clara River, amounts of this statistical criteria was 0.92 for the best WANN model, while it was 0.76, 0.78, and 0.39 for the best ANN, ANFIS, and SRC models, respectively. Also, the values of cumulative suspended sediment load computed by the best WANN model were closer to the observed data than the other models. In general, results indicated that the WANN model could satisfactorily mimic phenomenon, acceptably estimate cumulative SSL, and reasonably predict peak SSL values.

Recently, after 3 years, the German Bakery reopened its doors to its patrons. Eagerness hovers, but within the lines of prudence and security checks. The 2010 blasts that killed 17 and injured at least 60 people right there creates a certain curiosity to visit the German Bakery. While it was once a humble cafe with communal seating and self-service; the new German Bakery is now a swanky cafe with well informed waiters and an extended menu. It has been rebuilt and restructured to make the emotional people of Pune forget the dark past that it holds. This case study analyzed the current branding strategy of the German Bakery and made a comparison with its pre-existing model, that is, the model followed prior to February 2010. The case study aimed to highlight the concept of rebranding in the context of marketing strategies adopted by the German Bakery, and examined the steps taken by the owners to revamp and safeguard its premises post the 2010 blasts. The case study also took into account the customers' feedback about the revamped German Bakery, Pune.