What’s the Harm in Waiting? Examining disfluency from system response time in decision tasks with conversational agents

2023 | Americas Conference on Information Systems | Citations: 0

Authors: Duron, Edgar; Ray, Soumya; Hsia, Po Jen

Abstract: Using conversational agents as decision-support tools brings together an intere ... Expand

Abstract: Using conversational agents as decision-support tools brings together an interesting mix of theoretical lenses. On the one hand, user experiences with agents must still conform to characteristics of fluent use as any interactive system. But at the same time, the more human-like nature of back-and-forth discourse, instead of static graphical interfaces, provides users with social cues that they must then contend with. This study demonstrates how users facing disfluency, such as goal-oriented decision-making with large choice sets, can aid themselves with filters as a tool to reach the end of their task. It also demonstrates how a slowed system response (a social cue) will have a negative effect in disfluent situations where users are trying to regain confidence. A slowed system response time discourages users from using filters leaving them making a suboptimal decision. This study shows how decision fluency and social cues have interesting interactions in their effect on users performing tasks with conversational agents. Collapse

Topics: conversational agent decision making application programming interface Facebook Messenger social media

Methods: chatbot experiment regression analysis method factorial experiment descriptive statistic

Theories: social response theory

Analyzing the Quality of Twitter Data Streams

2022 | Information Systems Frontiers | Citations: 0

Authors: Arolfo, Franco; Rodriguez, Kevin Cortés; Vaisman, Alejandro

Abstract: There is a general belief that the quality of Twitter data streams is generally ... Expand

Abstract: There is a general belief that the quality of Twitter data streams is generally low and unpredictable, making, in some way, unreliable to take decisions based on such data. The work presented here addresses this problem from a Data Quality (DQ) perspective, adapting the traditional methods used in relational databases, based on quality dimensions and metrics, to capture the characteristics of Twitter data streams in particular, and of Big Data in a more general sense. Therefore, as a first contribution, this paper re-defines the classic DQ dimensions and metrics for the scenario under study. Second, the paper introduces a software tool that allows capturing Twitter data streams in real time, computing their DQ and displaying the results through a wide variety of graphics. As a third contribution of this paper, using the aforementioned machinery, a thorough analysis of the DQ of Twitter streams is performed, based on four dimensions: Readability, Completeness, Usefulness, and Trustworthiness. These dimensions are studied for several different cases, namely unfiltered data streams, data streams filtered using a collection of keywords, and classifying tweets referring to different topics, studying the DQ for each topic. Further, although it is well known that the number of geolocalized tweets is very low, the paper studies the DQ of tweets with respect to the place from where they are posted. Last but not least, the tool allows changing the weights of each quality dimension considered in the computation of the overall data quality of a tweet. This allows defining weights that fit different analysis contexts and/or different user profiles. Interestingly, this study reveals that the quality of Twitter streams is higher than what would have been expected. Collapse

Topics: Twitter data quality big data covid 19 application programming interface

Methods: experiment sentiment analysis literature study CoreNLP exploratory data analysis

Towards a Generation of Artificially Intelligent Strategy Tools: The SWOT Bot

2022 | European Conference On Information Systems | Citations: 0

Authors: Au, Christian; Winkler, Till; Paul, Herbert

Abstract: Strategy tools are widely used to inform the complex and unstructured decision ... Expand

Abstract: Strategy tools are widely used to inform the complex and unstructured decision making of firms. Although software has evolved to support strategy analysis, such digital strategy tools still require heavy manual work especially on the data input and processing levels, making their use time-intensive, costly, and susceptible to biases. This design research presents the 'SWOT Bot', a digital strategy tool that exploits recent advances in natural language processing (NLP) to perform a SWOT (strengths, weaknesses, opportunities, threats) analysis. Our artifact uses a feed reader, an NLP pipeline, and a visual interface to automatically extract information from a text corpus (e.g., analyst reports) and present it to the user. We argue that the SWOT Bot reduces time and adds objectivity to strategy analyses while allowing the human-in-the-loop to focus on value-adding tasks. Besides providing a functioning prototype, our work provides three general design principles for the development of next-generation digital strategy tools.Strategy tools-such as a SWOT, Porter's Five Forces, or the PEST model-are widely used among managers, analysts, and consultants in today's business practice (e.g., Jarzabkowski and Kaplan, 2014;Wright et al., 2013;Vaara andWhittington, 2012 andor Clark, 1997). While the term 'tool' generally refers to anything that helps perform a specific task, management tools cover any model, concept, framework, method, or technique that helps to solve a managerial problem (Hakala and Vuorinen, 2020; Jarzabkowski and Kaplan, 2014;Knott, 2008). Strategy tools are a subset of management tools that deal with strategic challenges, such as understanding a company's positioning and developing a new competitive strategy. Strategy tools are cognitive as well as material artifacts (Paroutis et al., 2015) that shape the mental models of strategists and hence affect both content and process of strategy work (Vuorinen et al., 2018). The application of strategy tools in practice is based on quantitative and qualitative inputs, where qualitative information seems to dominate. Although the use of strategy tools has evolved from pen and paper drawings to digital templates and dedicated software suites over the past decades (Ain et al., 2019;Arnott et al., 2017), our initial analysis found that digital tools for strategy available on the market lack support on the input, processing, and output levels. Contemporary digital strategy tools heavily rely on human tasks because strategic analysis is a complex process that integrates knowledge and data from heterogeneous and often unstructured sources (Hakala and Vuorinen, 2020;Jarzabkowski and Kaplan, 2015). While human involvement in strategy processes matters (Reeves and Ueda, 2016), it also comes with certain costs (Grant, 2016). Collapse

Topics: information systems strategy application programming interface Google+ SWOT analysis usability

Methods: natural language processing design artifact design science design requirement BERT

Where was COVID-19 first discovered? Designing a question-answering system for pandemic situations

2022 | European Conference On Information Systems | Citations: 0

Authors: Graf, Johannes; Lancho, Gino; Zschech, Patrick; Heinrich, Kai

Abstract: The COVID-19 pandemic is accompanied by a massive "infodemic" that makes it har ... Expand

Abstract: The COVID-19 pandemic is accompanied by a massive "infodemic" that makes it hard to identify concise and credible information for COVID-19-related questions, like incubation time, infection rates, or the effectiveness of vaccines. As a novel solution, our paper is concerned with designing a question-answering system based on modern technologies from natural language processing to overcome information overload and misinformation in pandemic situations. To carry out our research, we followed a design science research approach and applied Ingwersen's cognitive model of information retrieval interaction to inform our design process from a socio-technical lens. On this basis, we derived prescriptive design knowledge in terms of design requirements and design principles, which we translated into the construction of a prototypical instantiation. Our implementation is based on the comprehensive CORD-19 dataset, and we demonstrate our artifact's usefulness by evaluating its answer quality based on a sample of COVID-19 questions labeled by biomedical experts. Collapse

Topics: knowledge base pandemic covid 19 database system Elasticsearch

Methods: design artifact design principle design science question answering design requirement

A Multi-criteria Decision Support System for Ph.D. Supervisor Selection: A Hybrid Approach

2019 | HICSS | Citations: 0

Authors: Hasan, Mir Anamul; Schwartz, Daniel G

Abstract: Selection of a suitable Ph.D. supervisor is a very important step in a student’s ... Expand

Abstract: Selection of a suitable Ph.D. supervisor is a very important step in a student’s career. This paper presents a multi-criteria decision support system to assist students in making this choice. The system employs a hybrid method that first utilizes a fuzzy analytic hierarchy process to extract the relative importance of the identified criteria and sub-criteria to consider when selecting a supervisor. Then, it applies an information retrieval-based similarity algorithm (TF/IDF or Okapi BM25) to retrieve relevant candidate supervisor profiles based on the student’s research interest. The selected profiles are then re-ranked based on other relevant factors chosen by the user, such as publication record, research grant record, and collaboration record. The ranking method evaluates the potential supervisors objectively based on various metrics that are defined in terms of detailed domain-specific knowledge, making part of the decision making automatic. In contrast with other existing works, this system does not require the professor’s involvement and no subjective measures are employed. Collapse

Topics: information retrieval decision support system Elasticsearch database system systems implementation

Methods: Okapi BM25 computational algorithm survey term frequency–inverse document frequency trade-off analysis method

XLab: Early Indications & Warnings from Open Source Data with Application to Biological Threat

2018 | HICSS | Citations: 0

Authors: Simek, Olga; Davis, Curtis; Heier, Andrew; Mohindra, Sanjeev; O'Brien, Kyle; Passarelli, John; Waugh, Frederick

Abstract: XLab is an early warning system that addresses a broad range of national securit ... Expand

Abstract: XLab is an early warning system that addresses a broad range of national security threats using a flexible, rapidly reconfigurable architecture. XLab enables intelligence analysts to visualize, explore, and query a knowledge base constructed from multiple data sources, guided by subject matter expertise codified in threat model graphs. This paper describes a novel system prototype that addresses threats arising from biological weapons of mass destruction. The prototype applies knowledge extraction analytics-”including link estimation, entity disambiguation, and event detection-”to build a knowledge base of 40 million entities and 140 million relationships from open sources. Exact and inexact subgraph matching analytics enable analysts to search the knowledge base for instances of modeled threats. The paper introduces new methods for inexact matching that accommodate threat models with temporal and geospatial patterns. System performance is demonstrated using several simplified threat models and an embedded scenario. Collapse

Topics: knowledge graph knowledge base database system open source graph database

Methods: computational algorithm design artifact longitudinal research literature study named entity recognition