The Relationship Between Twitter Sentiment and Stock Performance: A Decision Tree Approach

2023 | HICSS | Citations: 0

Authors: Chen, Rongjuan; Dong, Ruoxi

Abstract: Social media has become a communication tool, but also a valuable database for r ... Expand

Abstract: Social media has become a communication tool, but also a valuable database for researchers and practitioners to gather information, share knowledge, as well as express opinions about stock performance. The sentiment embedded in social media content can be analyzed to predict stock performance. Although numerous past studies have attempted to predict stock price movement using social media sentiment, some emerging analytical tools, like existing lexicons, may require further testing and validation in a financial decision making context. In this study, we develop and test predictive models for stock price and trend forecasting. By using a large-scale sample of tweets collected from Twitter, related to four companies, Apple, Google, Microsoft, and Netflix, we propose a novel decision tree approach to stock performance prediction. Based on our findings, we then provide theoretical and practical implications and discuss the directions for future work. Collapse

Topics: Twitter social media decision making digital service Netflix

Methods: sentiment analysis decision tree classification regression analysis method multiple linear regression NLP tool

Theories: behavioral economics

Champions for Social Good: How Can We Discover Social Sentiment and Attitude-Driven Patterns in Prosocial Communication?

2023 | Journal of the Association for Information Systems | Citations: 0

Authors: Mukkamala, Raghava; Kauffman, Robert; Henriksen, Helle

Abstract: The UN High Commissioner on Refugees (UNHCR) is pursuing a social media strateg ... Expand

Abstract: The UN High Commissioner on Refugees (UNHCR) is pursuing a social media strategy to inform people about displaced populations and refugee emergencies. It is actively engaging public figures to increase awareness through its prosocial communications and improve social informedness and support for policy changes in its services. We studied the Twitter communications of UNHCR social media champions and investigated their role as high-profile influencers. In this study, we offer a design science research and data analytics framework and propositions based on the social informedness theory we propose in this paper to assess communication about UNHCR's mission. Two variables-refugee-emergency and champion type-relate to the informedness of UNHCR champions' followers. Based on a Twitter sentiment and attitude corpus, we applied a five-step design science analytics framework involving machine learning and natural language processing to test how the emergency type and champion type impact social communication patterns. Positive and neutral sentiment dominated the tweets of the champions and their followers for most refugee-emergency types. High participation-intensity champions emphasized high-intensity emergencies with tweet patterns reflecting dominant positive or neutral sentiment and sharing/liking attitudes. However, we found that sports figures effects were limited in spreading UNHCR's message, despite their millions of followers. We demonstrate the power of data science for prosocial policy based on refugee crisis awareness and instantiate our methods and knowledge contributions in a research framework that derives knowledge, decisions, and actions from behavioral, design, and economics of information systems perspectives. Collapse

Topics: Twitter social media analytical information system big data application programming interface

Methods: design science BERT natural language processing unsupervised learning artificial neural network

Theories: Lewin's field theory

Managing Group Confidence and Consensus in Intuitionistic Fuzzy Large Group Decision-Making Based on Social Media Data Mining

2022 | Group Decision and Negotiation | Citations: 0

Authors: Chen, Xiaohong; Zhang, Weiwei; Xu, Xuanhua; Cao, Wenzhi

Abstract: Social media has played an increasingly important role in decision-making for pu ... Expand

Abstract: Social media has played an increasingly important role in decision-making for public issues, and the concerns of the public, an important reference for which is in social media, have increasingly attracted attention in the field of large group decision-making (LGDM). On this basis, this paper presents a novel LGDM model based on social media data mining to manage group confidence and consensus. The proposed model comprises three processes, namely (1) term frequency-inverse document frequency (TF-IDF) keyword extraction, (2) the management of group confidence and consensus, (3) the selection process. In the first process, natural language processing (NLP) technology is used to extract keywords from social media data, and the topic of concern by the public is regarded as the evaluation criteria of decision-making alternatives. Then the TF-IDF weighting method is used to determine the weight of each criterion. Regarding the second process, the concept of the confidence correlation degree is defined, and a novel confidence-consensus model is proposed to manage group confidence and consensus. In the group consensus-reaching process (CRP), if the most incompatible cluster (or subgroup) has a higher confidence correlation degree regarding its own opinions, then it is advised that the weight of the cluster be reduced; if the most incompatible cluster has a lower confidence correlation degree regarding its own opinions, then it is advised that the cluster changes its opinions. In the third process, the weights of the criteria determined by the TF-IDF measure are aggregated, and the decision results are obtained. A case study is provided to illustrate the application of the proposed method, and the results of a comparative analysis reveal the features and advantages of this model. Collapse

Topics: social media decision making big data microblog Python

Methods: term frequency–inverse document frequency cluster analysis cross sectional research computational algorithm natural language processing

Theories: lemon market theory fuzzy set theory

Social media crowdsourcing for rapid damage assessment following a sudden-onset natural hazard event

2021 | International Journal of Information Management | Citations: 0

Authors: Li, Lingyao; Bensi, Michelle; Cui, Qingbin; Baecher, Gregory B.; Huang, You

Abstract: Rapid appraisal of damages related to hazard events is of importance to first re ... Expand

Abstract: Rapid appraisal of damages related to hazard events is of importance to first responders, government agencies, insurance industries, and other private and public organizations. While satellite monitoring, ground-based sensor systems, inspections and other technologies provide data to inform post-disaster response, crowdsourcing through social media is an additional and novel data source. In this study, the use of social media data, prin­ cipally Twitter postings, is investigated to make approximate but rapid early assessments of damages following a disaster. The goal is to explore the potential utility of using social media data for rapid damage assessment after sudden-onset hazard events and to identify insights related to potential challenges. This study defines a textbased damage assessment scale for earthquake damages, and then develops a text classification model for rapid damage assessment. Although the accuracy remains a challenge compared to ground-based instrumental readings and inspections, the proposed damage assessment model features rapidity with large amounts of data at spatial densities that exceed those of conventional sensor networks. The 2019 Ridgecrest, California earthquake sequence is investigated as a case study. Collapse

Topics: Twitter earthquake social media natural hazard Wikipedia

Methods: term frequency–inverse document frequency word embedding descriptive statistic statistical hypothesis test deep learning

From semantics to pragmatics: where IS can lead in Natural Language Processing (NLP) research

2021 | European Journal of Information Systems | Citations: 0

Authors: Li, Yan; Thomas, Manoj a; Liu, Dapeng

Abstract: Natural Language Processing (NLP) is now widely integrated into web and mobile a ... Expand

Abstract: Natural Language Processing (NLP) is now widely integrated into web and mobile applications, enabling natural interactions between humans and computers. Although there is a large body of NLP studies published in Information Systems (IS), a comprehensive review of how NLP research is conceptualised and realised in the context of IS has not been conducted. To assess the current state of NLP research in IS, we use a variety of techniques to analyse a literature corpus comprising 356 NLP research articles published in IS journals between 2004 and 2018. Our analysis indicates the need to move from semantics to pragmatics. More importantly, our findings unpack the challenges and assumptions underlying current research trends in NLP. We argue that overcoming these challenges will require a renewed disciplinary IS focus. By proposing a roadmap of NLP research in IS, we draw attention to three NLP research perspectives and present future directions that IS researchers are uniquely positioned to address. Collapse

Topics: database system knowledge representation social media analytics social media information retrieval

Methods: natural language processing qualitative content analysis literature study computational algorithm literature sample

An OOV-Aware Curation Process for Psycholinguistic Analysis of Social Media Text - A Hybrid Approach

2020 | DESRIST | Citations: 0

Authors: Liu, Kun; Li, Yan

Abstract: Massive user generated social media text posits new opportunities as well as cha ... Expand

Abstract: Massive user generated social media text posits new opportunities as well as challenges for psycholinguistic analysis to understand individual differences such as personality. Traditional off-the-shelf NLP (Natural Language Processing) tools perform poorly when analyzing text from social media because of the frequent out-of-vocabulary (OOV) words usage. Existing dictionary-based, closed-vocabulary approach and data-driven, open-vocabulary approach are both limited in handling OOV words. This research designs an OOV-aware curation process with a specific focus on OOV words. Following a design science research process model, the curation process is designed through four design cycles. The curation process includes a hybrid approach that integrates closed-vocabulary dictionary with expanded OOV categories and open-vocabulary approach with normalized OOV words. The curation process would enable psycholinguistic researchers and practitioners to exploit more psycholinguistic cues for tasks similar to personality predictions using social media text. Collapse

Topics: personality social media Python individual characteristic logistics management

Methods: design science experiment regression analysis method conceptual modelling ensemble learning

Towards Natural Language Processing: An Accounting Case Study

2020 | International Conference on Information Systems | Citations: 0

Authors: Mayer, Joerg Hans; Stritzel, Oliver; Esswein, Markus; Quick, Reiner

Abstract: Natural language processing (NLP) helps to extract data from digitized documents ... Expand

Abstract: Natural language processing (NLP) helps to extract data from digitized documents. An interesting use case occurred with the International Financial Reporting Standard 16. Following design science research in information systems, the objective of this article is to lay out design guidelines to automate data extraction from physical leasing contracts by applying NLP. Taking a leading international technology group in the areas of specialty glass and glass-ceramics as our case study, we discuss as follows: (1) The data format of the receiving IS is a sine qua non requirement of the project. Thus, set up the NLP process from the end of the project. (2) Evaluate machine readability of the input documents before preprocessing. List most frequent extraction issues in a manual early in the process. (3) Cluster documents regarding their structure and content beforehand. Then, apply a specifically trained ML algorithm for each cluster. (4) A trainer should guide the machine. Use recall and precision as measures. (5) Design an intuitive user interface by offering both parallel windows and a highlighting feature to offer a quick comparison even for complex contract documents. (6) Project iterations are worthwhile until a stable process is achieved. Collapse

Topics: database system user interface data quality accounting information retrieval

Methods: design guideline natural language processing qualitative interview case study data modeling

Theories: information systems success model technology acceptance model

An Ensemble of Ensembles Approach to Author Attribution for Internet Relay Chat Forensics

2020 | ACM Transactions on Management Information Systems | Citations: 0

Authors: Shao, Sicong; Tunc, Cihan; Al-Shawi, Amany; Hariri, Salim

Abstract: With the advances in Internet technologies and services, social media has been g ... Expand

Abstract: With the advances in Internet technologies and services, social media has been gained extreme popularity, especially because these technologies provide potential anonymity, which in turn harbors hacker discussion forums, underground markets, dark web, and so on. Internet relay chat (IRC) is a real-time communication protocol actively used by cybercriminals for hacking, cracking, and carding. Hence, it is particularly urgent to identify the authors of threat messages and malicious activities in IRC. Unfortunately, author identification studies in IRC remain as an underexplored area. In this research, we perform novel IRC text feature extraction methods and propose the first author attribution version of the deep forest (DF) model that is an ensemble of ensembles that utilizes the fusion of ensemble learning techniques. Our approach is supported by autonomic IRC monitoring. Experiments show that our approach is highly effective for author attribution and attains high accuracy even when the number of candidates is large while training data is limited. Collapse

Topics: personality IT security social media data security anonymity

Methods: experiment support vector machine ensemble learning decision tree classification LightGBM

Theories: big five model

Using NLP to Extract Predicate History from Medical Device Approvals

2020 | International Conference on Information Systems | Citations: 0

Authors: Zhu, Yi; Everhart, Alexander; Mandic, Pinar Karaca; Sen, Soumya

Abstract: The FDA approves new moderate-risk medical devices through the Pre-Market Notifi ... Expand

Abstract: The FDA approves new moderate-risk medical devices through the Pre-Market Notification (510(k)) process based on their similarity to previously cleared devices known as “predicates”. It is unknown how the features of predicates are associated with the safety of new devices. To address this issue, we employ Natural Language Processing (NLP) techniques to extract the complete list of predicates for each new device from their 510(k) documents and create a predicate database, based on which we assess the association between features of predicates and the likelihood of new devices’ recalls. The results help answer questions such as whether new devices with longer predicate history chain are more likely to be recalled and whether new devices with more predicates are more likely to be recalled. Our proposed data-driven approach for analyzing the role of predicates in the 510(k) process helps researchers explore how the process promotes the development of safe medical devices. Collapse

Topics: database system website health information system

Methods: natural language processing computational algorithm regression analysis method qualitative coding NLP tool

How Sentiment Impacts the Success of Blockchain Startups – An Analysis of Social Media Data and Initial Coin Offerings

2019 | HICSS | Citations: 0

Authors: Albrecht, Simon; Lutz, Bernhard; Neumann, Dirk

Abstract: The blockchain technology is subject to intensive discourse on social media. One ... Expand

Abstract: The blockchain technology is subject to intensive discourse on social media. One example is the promotion of Initial Coin Offerings (ICO) as a new financial instrument for startups. As ICOs are generally low-regulated, potential investors and entrepreneurs are faced with decision-making under uncertainty. This uncertainty might be partially offset by social factors. Based on established behavioral, economic and information systems theory, we investigate how different social media channels are linked to the capitalization of blockchain startups. We present empirical evidence from online search trends, financial data and a corpus of 231,758 tweets related to 524 ICOs. Our results suggest that higher search volume, positive sentiment and the increased use of emotive language on Twitter are linked to a high capitalization. The results are relevant for startups and potential ICO investors. Collapse

Topics: Twitter blockchain social media Google+ value creation

Methods: descriptive statistic regression analysis method linear regression analysis longitudinal research time series analysis

Theories: information systems theory behavioral economics