Is a Pretrained Model the Answer to Situational Awareness Detection on Social Media?

2023 | HICSS | Citations: 0

Authors: Lo, S.; Lee, K.; Zhang, Y.

Abstract: Social media can be valuable for extracting information about an event or incid ... Expand

Abstract: Social media can be valuable for extracting information about an event or incident on the ground. However, the vast amount of content shared, and the linguistic variants of languages used on social media make it challenging to identify important situational awareness content to aid in decision-making for first responders. In this study, we assess whether pretrained models can be used to address the aforementioned challenges on social media. Various pretrained models, including static word embedding (such as Word2Vec and GloVe) and contextualized word embedding (such as DistilBERT) are studied in detail. According to our findings, a vanilla DistilBERT pretrained language model is insufficient to identify situation awareness information. Fine-tuning by using datasets of various event types and vocabulary extension is essential to adapt a DistilBERT model for real-world situational awareness detection. Collapse

Topics: Twitter situational awareness social media Wikipedia wiki

Methods: BERT DistilBERT support vector machine machine learning word embedding

Getting Personal: A Deep Learning Artifact for Text-Based Measurement of Personality

2023 | Information Systems Research | Citations: 0

Authors: Yang, Kai; Lau, Raymond Y. K.; Abbasi, Ahmed

Abstract: Analysts, managers, and policymakers are interested in predictive analytics capa ... Expand

Abstract: Analysts, managers, and policymakers are interested in predictive analytics capable of offering better foresight. It is generally accepted that in forecasting scenarios involving organizational policies or consumer decision making, personal characteristics, including personality, may be an important predictor of downstream outcomes. The inclusion of personality features in forecasting models has been hindered by the fact that traditional measurement mechanisms are often infeasible. Text-based personality detection has garnered attention because of the public availability of digital textual traces. However, the text machine learning space has bifurcated into two branches: feature-based methods relying on manually crafted human intuition, or deep learning language models that leverage big data and compute, the main commonality being that neither branch generates accurate personality assessments, thereby making personality measures infeasible for downstream forecasting applications. In this study, we propose DeepPerson, a design artifact for text-based personality detection that bridges these two branches by leveraging concepts from relevant psycholinguistic theories in conjunction with advanced deep learning strategies. DeepPerson incorporates novel transfer learning and hierarchical attention network methods that use psychological concepts and data augmentation in conjunction with person-level linguistic information. We evaluate the utility of the proposed artifact using an extensive design evaluation on three personality data sets in comparison with state-of-the-art methods proposed in academia and industry. DeepPerson can improve detection of personality dimensions by 10–20 percentage points relative to the best comparison methods. Using case studies in the finance and health domains, we show that more accurate text-based personality detection can translate into significant improvements in downstream applications such as forecasting future firm performance or predicting pandemic infection rates. Our findings have important implications for research at the intersection of design and data science, and practical implications for managers focused on enabling, producing, or consuming predictive analytics.History: Olivia Sheng, Senior Editor; Huimin Zhao, Associate Editor.Funding: This work was supported by Oracle for Research (NLP for the Greater Good) and the U.S. National Science Foundation’s Division of Information and Intelligent Systems [Grants BDS-1636933 and IIS-1816504]. The work was also partly supported by the Research Grants Council of the Hong Kong Special Administrative Region [Project: CityU 11507219] and the City University of Hong Kong SRG [Project: 7005780].Supplemental Material: The online appendices are available at https://doi.org/10.1287/isre.2022.1111. Collapse

Topics: personality Twitter social media pandemic Google+

Methods: machine learning BERT design science deep learning computational algorithm

Theories: big five model

Transformer-based Summarization and Sentiment Analysis of SEC 10-K Annual Reports for Company Performance Prediction

2022 | HICSS | Citations: 0

Authors: Hsieh, Hsin-Ting; Hristova, Diana

Abstract: Annual reports published by companies contain important insights regarding their ... Expand

Abstract: Annual reports published by companies contain important insights regarding their performance and are often analyzed in a manual, subjective manner. We address this point by combining the streams of research on text summarization and topic modelling with the one on sentiment analysis. Our approach consists of the steps of text summarization using BERTSUMEXT, topic modelling with LDA, sentiment analysis with FinBERT, and performance prediction with Decision Trees and Random Forest. The result provides decision makers with an interpretable and condensed representation of the content of annual reports, together with its relationship to future company performance. We evaluate our approach on 10-K reports, demonstrating both its interpretability for analysts and explanatory power regarding future company performance. Collapse

Topics: organizational productivity data breach cloud computing Python explainable artificial intelligence

Methods: sentiment analysis topic model machine learning BERT decision tree classification

Research Method Classification with Deep Transfer Learning for Semi-Automatic Meta-Analysis of Information Systems Papers

2021 | HICSS | Citations: 0

Authors: Anisienia, Anna; Mueller, Roland M.; Kupfer, Anna; Staake, Thorsten

Abstract: This paper presents an artifact that uses deep transfer learning methods for the ... Expand

Abstract: This paper presents an artifact that uses deep transfer learning methods for the multi-label classification of research methods for an Information Systems corpus. The artifact can support researchers with frequently performed yet time-consuming classification and structure-seeking tasks that are often part of literature analyses. We use a corpus of 5,388 papers from AIS journals and conferences, of which 1,766 have been manually labelled with up to five research methods. The unlabelled papers are used for finetuning the language model, whereas the labelled data are used for training and testing. Our approach outperforms state of the art research method classification that deploy SVM. We show that deep transfer learning models can lead to a better recognition of research methods than shallower word embedding approaches like word2vec or GloVe. The results illustrate the potential of establishing semiautomated methods for meta-analysis. Collapse

Topics: database system knowledge type knowledge representation

Methods: literature sample GloVe support vector machine experiment language model

Leveraging Natural Language Processing to Analyze Scientific Content: Proposal of an NLP pipeline for the field of Computer Vision

2021 | International Conference on Business Informatics | Citations: 0

Authors: Kortum, Henrik; Leimkühler, Max; Thomas, Oliver

Abstract: In this paper we elaborate the opportunity of using natural language processing ... Expand

Abstract: In this paper we elaborate the opportunity of using natural language processing to analyze scientific content both, from a practical as well as a theoretical point of view. Firstly, we conducted a literature review to summarize the status quo of using natural language processing for analyzing scientific content. We could identify different approaches, e.g., with the aim of clustering and tagging publications or to summarize scientific papers. Secondly, we conducted a case study where we used our proposed natural language processing pipeline to analyze scientific content about computer vision available at the database IEEE. Our method helped us to identify emerging trends in the recent years and give an overview of the field of research. Collapse

Topics: digital ecosystem open innovation database system Python

Methods: natural language processing literature study image processing case study deep learning

Classifying Mental Health Conditions Via Symptom Identification: A Novel Deep Learning Approach

2019 | International Conference on Information Systems | Citations: 0

Authors: Davcheva, Elena

Abstract: An increasing number of individuals around the world suffer from mental health i ... Expand

Abstract: An increasing number of individuals around the world suffer from mental health issues but are unable to access professional help as resources are lacking on a global level. Information technology and especially machine learning has shown great potential as a basis for automated digital services that can act as a support tool for affected individuals. This study presents a state-of-the-art deep learning model for multiclass classification of mental health conditions based on a novel approach of prior classification of symptoms. We contribute to existing research on IS applications in healthcare by improving upon the performance of similar previously reported models, as well as showing that unstructured text can be used to reliably extract not only a primary but also a secondary condition classification. We show that classifying symptoms of individual conditions first and based on that result extracting conditions leads to better model performance. Collapse

Topics: Python online learning system health information system privacy system support

Methods: artificial neural network machine learning deep learning recurrent neural network experiment