Ensembles of Text and Time-Series Models for Automatic Generation of Financial Trading Signals from Social Media Content

2018 ◽  
Vol 29 (1) ◽  
pp. 753-772 ◽  
Author(s):  
Omar A. Bari ◽  
Arvin Agah
Keyword(s):  
Social Media ◽  
Stock Prices ◽  
Clustering Algorithm ◽  
Event Studies ◽  
Time Series Models ◽  
Media Content ◽  
Trading Decisions ◽  
Event Clustering ◽  
Sharpe Ratios ◽  
News Headlines

Abstract Event studies in finance have focused on traditional news headlines to assess the impact an event has on a traded company. The increased proliferation of news and information produced by social media content has disrupted this trend. Although researchers have begun to identify trading opportunities from social media platforms, such as Twitter, almost all techniques use a general sentiment from large collections of tweets. Though useful, general sentiment does not provide an opportunity to indicate specific events worthy of affecting stock prices. This work presents an event clustering algorithm, utilizing natural language processing techniques to generate newsworthy events from Twitter, which have the potential to influence stock prices in the same manner as traditional news headlines. The event clustering method addresses the effects of pre-news and lagged news, two peculiarities that appear when connecting trading and news, regardless of the medium. Pre-news signifies a finding where stock prices move in advance of a news release. Lagged news refers to follow-up or late-arriving news, adding redundancy in making trading decisions. For events generated by the proposed clustering algorithm, we incorporate event studies and machine learning to produce an actionable system that can guide trading decisions. The recommended prediction algorithms provide investing strategies with profitable risk-adjusted returns. The suggested language models present annualized Sharpe ratios (risk-adjusted returns) in the 5–11 range, while time-series models produce in the 2–3 range (without transaction costs). The distribution of returns confirms the encouraging Sharpe ratios by identifying most outliers as positive gains. Additionally, machine learning metrics of precision, recall, and accuracy are discussed alongside financial metrics in hopes of bridging the gap between academia and industry in the field of computational finance.

scholarly journals Early detection of emergency events from social media: A new text clustering approach

2021 ◽  
Author(s):  
Lida Huang ◽  
Panpan Shi ◽  
Haichao Zhu ◽  
Tao Chen
Keyword(s):  
Social Media ◽  
Early Detection ◽  
Clustering Algorithm ◽  
Integrated Approach ◽  
Practical Applications ◽  
Emergency Event ◽  
Attribute Information ◽  
Event Clustering ◽  
Clustering Approach ◽  
Emergency Events

Abstract Emergency events need early detection, quick response, and accuracy recover. In the era of big data, social media users can be seen as social sensors to monitor real time emergency events. This paper proposed an integrated approach to early detect all the four kinds of emergency events including natural disasters, man-made accidents, public health events and social security events. First, the BERT-Att-BiLSTM model is used to detect emergency related posts from the massive and irrelevant data. Then, the 3W attribute information (What, Where and When) of the emergency event is extracted. With the 3W attribute information, we create an unsupervised dynamical event clustering algorithm based on text-similarity and combine it with the supervised logistical regression model to cluster posts into different events. The experiments on Sina Weibo data demonstrate the superiority of the proposed framework. Case studies on some real emergency events show the proposed framework has good performance and high timeliness. Practical applications of the framework have also been discussed, following by some future directions for improvement.

Marketing communication objectives through digital content marketing on social media

2020 ◽  
pp. 79-104
Author(s):  
Janice J. Nieves-Casasnovas ◽  
Frank Lozada-Contreras
Keyword(s):  
Social Media ◽  
Marketing Strategies ◽  
Brand Awareness ◽  
Digital Content ◽  
Media Content ◽  
Marketing Communication ◽  
Case Study Design ◽  
Multiple Case ◽  
Content Marketing

The purpose of this study was to determine what type of marketing communication objectives are present in the digital content marketing developed by luxury auto brands with social media presence in Puerto Rico, particularly Facebook. A longitudinal multiple-case study design was used to analyze five luxury auto brands using content analysis on Facebook posts. This analysis included identification of marketing communication objectives through social media content marketing strategies, type of media content and social media metrics. Our results showed that the most used objectives are brand awareness, brand personality, and brand salience. Another significant result is that digital content marketing used by brands in social media are focused towards becoming more visible and recognized; also, reflecting human-like traits and attitudes in their social media.

The Use of Social Media by the Botswana Government and Governance of Liquid Communication

Mousaion ◽  
2019 ◽  
Vol 37 (1) ◽  
Author(s):  
Tshepho Lydia Mosweu
Keyword(s):  
Social Media ◽  
Customer Service ◽  
Community Involvement ◽  
Media Content ◽  
Service Access ◽  
Communication Tool ◽  
African Countries ◽  
The World ◽  
The Government ◽  
Use Of Social Media

Social media as a communication tool has enabled governments around the world to interact with citizens for customer service, access to information and to direct community involvement needs. The trends around the world show recognition by governments that social media content may constitute records and should be managed accordingly. The literature shows that governments and organisations in other countries, particularly in Europe, have social media policies and strategies to guide the management of social media content, but there is less evidence among African countries. Thus the purpose of this paper is to examine the extent of usage of social media by the Botswana government in order to determine the necessity for the governance of liquid communication. Liquid communication here refers to the type of communication that goes easily back and forth between participants involved through social media. The ARMA principle of availability requires that where there is information governance, an organisation shall maintain its information assets in a manner that ensures their timely, efficient and accurate retrieval. The study adopted a qualitative case study approach where data were collected through documentary reviews and interviews among purposively selected employees of the Botswana government. This study revealed that the Botswana government has been actively using social media platforms to interact with its citizens since 2011 for increased access, usage and awareness of services offered by the government. Nonetheless, the study revealed that the government had no official documentation on the use of social media, and policies and strategies that dealt with the governance of liquid communication. This study recommends the governance of liquid communication to ensure timely, efficient and accurate retrieval when needed for business purposes.

Motivating Exercise Through Social Media: Is a Picture Always Worth a Thousand Words?

2018 ◽  
Author(s):  
Caitlyn Johnston ◽  
William E. Davis
Keyword(s):  
Social Media ◽  
Individual Differences ◽  
Experimental Design ◽  
Health Behaviors ◽  
Media Content ◽  
Exercise Motivation ◽  
Positive Health ◽  
Content Type ◽  
Within Subjects

In the present study, we examined how the influence of exercise-related social media content on exercise motivation might differ across content type (with images vs. without images) and account type (individual vs. corporate). Using a 2 × 2 within-subjects experimental design, 229 participants viewed a series of 40 actual social media posts across the four conditions (individual posts with images, corporate posts with images, individual posts without images, and corporate posts without images) in a randomized order. Participants rated the extent to which they felt each social media post motivated them to exercise, would motivate others to exercise, and was posted for extrinsic reasons. Participants also completed other measures of individual differences including their own exercise motivation. Posts with images from individuals were more motivating than posts with images from corporations; however, corporate posts without images were more motivating than posts without images from individuals. Participants expected others to be similarly motivated by the stimuli, and perceived corporate posts as having been posted for more extrinsic reasons than individuals’ posts. These findings enhance our understanding of how social media may be used to promote positive health behaviors.

scholarly journals Mixed-methods process evaluation of SafeTea: a multimedia campaign to prevent hot drink scalds in young children and promote burn first aid

2020 ◽  
pp. injuryprev-2020-043909
Author(s):  
Laura Elizabeth Cowley ◽  
C Verity Bennett ◽  
Isabelle Brown ◽  
Alan Emond ◽  
Alison Mary Kemp
Keyword(s):  
Social Media ◽  
Mixed Methods ◽  
Young Children ◽  
Process Evaluation ◽  
Behavioural Change ◽  
First Aid ◽  
Multifaceted Intervention ◽  
Media Content ◽  
Educational Videos ◽  
The Uk

ObjectivesSafeTea is a multifaceted intervention delivered by community practitioners to prevent hot drink scalds to young children and improve parents’ knowledge of appropriate burn first aid. We adapted SafeTea for a national multimedia campaign, and present a mixed-methods process evaluation of the campaign.MethodsWe used social media, a website hosting downloadable materials and media publicity to disseminate key messages to parents/caregivers of young children and professionals working with these families across the UK. The SafeTea campaign was launched on National Burns Awareness Day (NBAD), October 2019, and ran for 3 months. Process evaluation measurements included social media metrics, Google Analytics, and quantitative and qualitative results from a survey of professionals who requested hard copies of the materials via the website.ResultsFindings were summarised under four themes: ‘reach’, ‘engagement’, ‘acceptability’ and ‘impact/behavioural change’. The launch on NBAD generated widespread publicity. The campaign reached a greater number of the target audience than anticipated, with over 400 000 views of the SafeTea educational videos. Parents and professionals engaged with SafeTea and expressed positive opinions of the campaign and materials. SafeTea encouraged parents to consider how to change their behaviours to minimise the risks associated with hot drinks. Reach and engagement steadily declined after the first month due to reduced publicity and social media promotion.ConclusionThe SafeTea campaign was successful in terms of reach and engagement. The launch on NBAD was essential for generating media interest. Future campaigns could be shorter, with more funding for additional social media content and promotion.

scholarly journals Examining Perceived and Projected Destination Image: A Social Media Content Analysis

2021 ◽  
Vol 13 (6) ◽  
pp. 3354
Author(s):  
Wei Sun ◽  
Shoulian Tang ◽  
Fang Liu
Keyword(s):  
Social Media ◽  
Content Analysis ◽  
Destination Image ◽  
Media Content ◽  
Media Content Analysis ◽  
Poor Understanding ◽  
Practical Implications

Destination image has been extensively studied in tourism and marketing, but the questions surrounding the discrepancy between the projected (perceptions from the National Tourism Organizations) and perceived destination image (perceptions from tourists) as well as how the discrepancy may influence sustainable experience remain unclear. Poor understanding of the discrepancy may cause tourist confusion and misuse of resources. The aim of this study is to empirically investigate if the perceived (by tourists) and projected (by NTOs) destination image are significantly different in both cognitive and affective aspects. Through a comprehensive social media content analysis of the NTO-generated and tourist-generated-contents (TGC), the current study identifies numerous gaps between the projected and perceived destination image, which offers some important theoretical and practical implications on destination management and marketing.

scholarly journals DAViS: a unified solution for data collection, analyzation, and visualization in real-time stock market prediction

2021 ◽  
Vol 7 (1) ◽  
Author(s):  
Suppawong Tuarob ◽  
Poom Wettayakorn ◽  
Ponpat Phetchai ◽  
Siripong Traivijitkhun ◽  
Sunghoon Lim ◽  
...  
Keyword(s):  
Machine Learning ◽  
Social Media ◽  
Data Collection ◽  
Stock Market ◽  
Real Time ◽  
Stock Prices ◽  
Contextual Information ◽  
Online News ◽  
Stock Prediction ◽  
Stock Market Prediction

AbstractThe explosion of online information with the recent advent of digital technology in information processing, information storing, information sharing, natural language processing, and text mining techniques has enabled stock investors to uncover market movement and volatility from heterogeneous content. For example, a typical stock market investor reads the news, explores market sentiment, and analyzes technical details in order to make a sound decision prior to purchasing or selling a particular company’s stock. However, capturing a dynamic stock market trend is challenging owing to high fluctuation and the non-stationary nature of the stock market. Although existing studies have attempted to enhance stock prediction, few have provided a complete decision-support system for investors to retrieve real-time data from multiple sources and extract insightful information for sound decision-making. To address the above challenge, we propose a unified solution for data collection, analysis, and visualization in real-time stock market prediction to retrieve and process relevant financial data from news articles, social media, and company technical information. We aim to provide not only useful information for stock investors but also meaningful visualization that enables investors to effectively interpret storyline events affecting stock prices. Specifically, we utilize an ensemble stacking of diversified machine-learning-based estimators and innovative contextual feature engineering to predict the next day’s stock prices. Experiment results show that our proposed stock forecasting method outperforms a traditional baseline with an average mean absolute percentage error of 0.93. Our findings confirm that leveraging an ensemble scheme of machine learning methods with contextual information improves stock prediction performance. Finally, our study could be further extended to a wide variety of innovative financial applications that seek to incorporate external insight from contextual information such as large-scale online news articles and social media data.

Building a Personal Brand as a CEO: A Case Study of Vivy Yusof, the Cofounder of FashionValet and the dUCk Group

SAGE Open ◽  
2021 ◽  
Vol 11 (3) ◽  
pp. 215824402110302
Author(s):  
Nor Hasliza Md Saad ◽  
Zulnaidi Yaacob
Keyword(s):  
Social Media ◽  
Building Blocks ◽  
Media Content ◽  
Fashion Industry ◽  
Personal Brand ◽  
Branding Strategies ◽  
Social Media Presence ◽  
Personal Branding ◽  
The Masses

Social media is a new platform for CEOs to build their image and create a strong personal brand to represent themselves and their company. This research examines an outstanding Malaysian fashion icon and social media–savvy businesswoman with over a million followers on Instagram, Vivy Yusof, the youngest Malaysian e-commerce mogul and an example of a successful CEO who has used personal branding to build an empire in the fashion industry. The objectives of this research are to identify the type of messages Vivy Yusof communicates to her audience through her personal Instagram posts and to identify the ways Vivy Yusof’s audience engages with her posts on Instagram. Her Instagram post content is classified using the Honeycomb framework that comprises seven functional building blocks, namely, presence, relationships, reputation, groups, identity, conversations, and sharing. In this study, the content of Vivy Yusof’s Instagram posts is categorized by how she focuses on the various functional building blocks in her posts and the implications these blocks have on how her audience interacts with the posts. Her social media presence confirms the importance of CEO personal branding because of her role and influence on the masses evidenced by the willingness of her followers to interact (through likes and comments) and engage with her posts on any subject matter, relating either to her business or personal life. The study contributes to a growing body of literature on personal branding strategies by shedding light on the association between content strategies and engagement with social media content.

Sign in / Sign up

Export Citation Format

Share Document