Results for “Sentiment analysis”

NASA NTRS2014

Sentiment of Search: KM and IT for User Expectations

User perceived value is the number one indicator of a successful implementation of KM and IT collaborations. The system known as "Search" requires more strategy and workflow that a mere data dump or ungoverned infrastructure can provide. Monitoring of user sentiment can be a driver for providing objective measures of success and justifying changes to the user interface. The dynamic nature of information technology makes traditional usability metrics difficult to identify, yet easy to argue against. There is little disagreement, however, on the criticality of adapting to user needs and expectations. The Systems Usability Scale (SUS), developed by John Brook in 1986 has become an industry standard for usability engineering. The first phase of a modified SUS, polls the sentiment of representative users of the JSC Search system. This information can be used to correlate user determined value with types of information sought and how the system is (or is not) meeting expectations. Sentiment analysis by way of the SUS assists an organization in identification and prioritization of the KM and IT variables impacting user perceived value. A secondary, user group focused analysis is the topic of additional work that demonstrates the impact of specific changes dictated by user sentiment.

Berndt, Sarah Ann↗

NASA NTRSDate not supplied

Knowledge Discovery for Early Failure Assessment of Complex Engineered Systems Using Natural Language Processing

Emerging complex engineered systems may have unexpected safety issues due to novel operational environments, increasing autonomy, human-machine interaction, and other factors. To prevent failures in operation or testing that necessitate costly redesign, it is desirable to predict likely failure modes early in the design process. Text-based information about past engineering failures presents one possible solution by facilitating the retrieval of information that can inform new designs. However, identifying documents containing relevant information and extracting required information can be prohibitively time-consuming when implemented at scale. In this research, an automated natural language processing-based framework is proposed to discover relevant knowledge from documents containing failure-related design information. Documents containing usable information are filtered using sentiment analysis based on a custom lexicon specialized for engineering design and by filtering out documents containing only irrelevant topics. Next, from the identified usable documents, information relating to engineering failures, contributing factors that can be controlled at design time (“risk factors”), and recommended preventative actions are extracted. Semantic similarity is then used to group similar pieces of extracted information for improved generalizability. The proposed framework is applied to NASA’s Lessons Learned Information System (LLIS). The framework can be used to identify documents containing usable failure-related design information from other databases, extract relevant information from these documents, and generalize the acquired knowledge such that it can be applied to novel systems.

Sequoia R. Andrade↗

NASA NTRSDate not supplied

Understanding and Verifying Neural Networks

Deep Neural Networks (DNNs) have gained immense popularity in recent times and have widespread use in applications such as image classification, sentiment analysis, speech recognition and also in safety-critical applications such as autonomous driving. However, they suffer limitations such as lack of explainability and robustness which raise safety and security concerns in their usage. Further, the complex structure and large input spaces of DNNs act as an impediment to thorough verification and testing. The SafeDNN project at the Robust Software Engineering (RSE) group at NASA aims at exploring techniques to ensure that systems that use deep neural networks are safe, robust and interpretable. In this talk, I will be presenting our technique Prophecy that automatically infers formal properties of deep neural network models. The tool extracts patterns based on neuron activations as preconditions that imply certain desirable output properties of the model. I would be highlighting case studies that use Prophecy in obtaining explanations for network decisions, understanding correct and incorrect behavior, providing formal guarantees wrt safety and robustness, and debugging neural network models. We have applied the tool on image classification networks, neural network controllers providing turn advisories in unmanned aircrafts, regression models used for autonomous center-line tracking in aircrafts and neural network object detectors

Deep Neural Networks↗

NASA NTRSDate not supplied

Language Model For Earth Science: Exploring Potential Downstream Applications As Well As Current Challenges

The use of deep learning techniques to build transformer language models such as SciBERT and GPT3 have transformed the natural language technology (NLT) landscape. These new NLTs are being used in speech to text and vice versa, auto-mated text classification, sentiment analysis, topic modeling, text summarization, and cognitive assistants. While Earth science has no shortage of unstructured data such as journal and conference papers, little efforts have focused on harnessing NLTs for knowledge extraction and supporting the scientific process. This paper surveys the use of language models in different science. BERT-E, a new Earth science-specific language model, is presented. BERT-E is generated using a transfer learning solution. A language model that has already been trained for general Science (SciBERT) is fine-tuned using abstracts and full text extracted from various Earth science-related articles. A downstream keywords classification application is used for evaluation, and the use of BERT-E shows improved performance. The need to develop a robust set of benchmarks in evaluating the language model such as BERT-E is discussed. Finally, example applications are presented to inspire additional ideas for applications using domain-specific language models.

R Ramachandran↗

NASA NTRS2025

Navigating Team Dynamics: Automated Detection of Micro-Behaviors Between Team Members Through Longitudinal Interaction Data

The success in future long term space exploration missions will depend on the cooperation, coordination, and mutual understanding among the crew members. Micro-behaviors are momentary, subtle linguistic and paralinguistic indicators of thinking and feeling toward another member of the team (Cortina et al., 2001; Smith & Griffiths, 2022) that can significantly impact team dynamics and influence the overall team performance (Paromita & Chaspari, 2024). Due to their interactive nature, micro-behaviors have a sender (i.e., the team member expressing the micro-behavior) and a target (the team member impacted by the micro-behavior). Detection of these behaviors can assist in avoiding possible conflict among crew members and promoting the overall team success. Our prior research focused on an initial proof of concept of machine learning (ML) models and natural language processing (NLP) techniques that were used for automatically detect micro-behaviors among crew members of the US National Aeronautics and Space Administration’s (NASA) Human Exploration Research Analog (HERA) Campaigns 4 and 5 missions (Paromita et al., 2023). Results underscored the importance of incorporating contextual information in the ML models in the form of sentiment analysis, type of task, and dyadic interaction among team members. Here, we expand the scope of our prior work in two ways. First, we assess ML/NLP methods on new behavioral annotations coded using an adapted version of Smith & Griffins (2022) theoretical framework in terms of Violation (i.e., presence of valenced behavior, uplifting/positive or discouraging/negative), Intensity (i.e., force of behavior in terms of how uplifting or discouraging is the behavior), and Intent (i.e., motive of the behavior in terms of whether it was deliberate or unintentional). Second, we expand the design of the ML model to preserve information about the role of each team member within the occurrence of the micro-behavior (in contrast to the previous model that only considered the sender and the target without determining the team member role). This allows to consider all team members' contributions in the conversation and model long-term dependencies in the dialogue. Our experiments for this study are conducted on data from 5 teams of the NASA HERA C4 (NASA grant NNX16AQ48G (PI: Bell)). Conversations were extracted from the 1.5 hour Team Interaction Battery (TIB) task that occurred 5 times in-mission per crew. This resulted in a total of 13,058 conversational turns (i.e., 17.8% uplifting, 3.3% discouraging, 75.76% neutral, 3.14% nulls). Our findings with the revised behavioral coding and ML/NLP models indicate a 43.66% macro F1-score (i.e., 38.29% precision (P), 50.8% recall (R)) for a dialog state-tracking model that includes information from the sender only, and a 40.9% F1-score (i.e., 38.7% P, 43.36% R) for the same model that includes information from both the sender and the target of the micro-behavior. These are significantly higher compared to simple random forest models that classify behaviors strictly based on speech content and do not consider iterative team dynamics, achieving a 36.07% F1-score (i.e., 39.04% R, 33.53% P). Our findings demonstrate potential ways to leverage large conversational datasets to better capture complex team dynamics. We will discuss future directions including proposed models that can incorporate additional mission days and tasks beyond the TIB for objectively quantifying team behavior at high temporal resolution in space exploration missions.

Projna Paromita↗

NASA NTRS2017

Understanding the International Space Station Crew Perspective following Long-Duration Missions through Data Analytics & Visualization of Crew Feedback

The International Space Station (ISS) first became a home and research laboratory for NASA and International Partner crewmembers over 16 years ago. Each ISS mission lasts approximately 6 months and consists of three to six crewmembers. After returning to Earth, most crewmembers participate in an extensive series of 30+ debriefs intended to further understand life onboard ISS and allow crews to reflect on their experiences. Examples of debrief data collected include ISS crew feedback about sleep, dining, payload science, scheduling and time planning, health & safety, and maintenance. The Flight Crew Integration (FCI) Operational Habitability (OpsHab) team, based at Johnson Space Center (JSC), is a small group of Human Factors engineers and one stenographer that has worked collaboratively with the NASA Astronaut office and ISS Program to collect, maintain, disseminate and analyze this data. The database provides an exceptional and unique resource for understanding the "crew perspective" on long duration space missions. Data is formatted and categorized to allow for ease of search, reporting, and ultimately trending, in order to understand lessons learned, recurring issues and efficiencies gained over time. Recently, the FCI OpsHab team began collaborating with the NASA JSC Knowledge Management team to provide analytical analysis and visualization of these over 75,000 crew comments in order to better ascertain the crew's perspective on long duration spaceflight and gain insight on changes over time. In this initial phase of study, a text mining framework was used to cluster similar comments and develop measures of similarity useful for identifying relevant topics affecting crew health or performance, locating similar comments when a particular issue or item of operational interest is identified, and providing search capabilities to identify information pertinent to future spaceflight systems and processes for things like procedure development and training. In addition, the comments were scored for sentiment using a polarity scoring algorithm to identify both positive and negative comments for particular groups and clusters, allowing the team to make analytically informed decisions regarding future hardware and operating procedures. The use of polarity scoring with time series analysis was used to provide insight into how crew health and habitability is changing throughout various spaceflight increments or the station lifecycle as a whole. Finally, a visualization framework was developed to address the needs of the end users to search for and analyze comments by user, category or mission. This paper will discuss how the use of an analytical framework in conjunction with the current human interface, improved the understanding of crew perspective and shortened the time for analysis allowing for more informed decisions and rapid development of improvements. These methods are significantly optimizing the way that this valuable data can be assessed and applied to current and future spaceflight design and development. This collaboration allows the FCI OpsHab team to effectively analyze and share data in a more automated and timely fashion. Trends are no longer derived manually and can be illustrated effectively and accurately with these evolving techniques to an ever growing group of human spaceflight end users.

Bryant, Cody↗

NASA NTRS2018

User Metrics in NASA Earth Science Data Systems

This presentation the collection and use of user metrics in NASA's Earth Science data systems. A variety of collection methods is discussed, with particular emphasis given to the American Customer Satisfaction Index (ASCI). User sentiment on potential use of cloud computing is presented, with generally positive responses. The presentation also discusses various forms of automatically collected metrics, including an example of the relative usage of different functions within the Giovanni analysis system.

user metrics↗

NASA NTRSDate not supplied

An Approach to Identifying Aspects of Positive Pilot Behavior within the Aviation Safety Reporting System

The National Airspace System (NAS) is constantly evolving as air traffic continues to ramp up to pre-pandemic numbers and projected to grow to unprecedented levels in the coming years. As well as increasing demand to the current system, emerging operations such as Unmanned Autonomous Systems are also expected to add to complexity in the airspace. To address these issues, the industry and government agencies supporting the NAS will need to rely upon additional automation and new technologies to address future operational requirements, while continuing to be a world-leading safe transportation system. As these new technologies are implemented, the system continues to rely on human pilots and controllers in the loop to monitor the system and intervene in situations the automation cannot handle. The goal of proactively addressing safety is of foremost concern to ensure passenger confidence. The industry has implemented various Safety Monitoring Systems to identify safety risks and proactively address them before they result in a serious incident or accident. One such program is the Aviation Safety Reporting System (ASRS). ASRS is a long-established system where pilots and controllers voluntarily and anonymously report safety incidents they experienced and observed during line operations by providing rich text narratives describing the events, the environment, and conditions leading to the safety event of concern. These narratives provide insight and context around events of interest and can be used to identify emerging problems. They can trigger investigations within Flight Operational Quality Assurance or Flight Data Monitoring programs. However, this process typically focuses on the adverse events and the unsafe aspects of the operations surrounding the reported or detected events. This perspective of investigating factors that went wrong around an adverse event is commonly referred to as Safety I. Alternatively, characterizing successful actions that operators perform every day under varying conditions that keep the system within safe operating bounds is a concept referred to as Safety II. The benefit of the Safety II view is that the scope is much larger than that of Safety I since a vast majority of the operations result in successful flights. Many of the successful techniques used to manage operational threats are not documented in standard operating procedures or taught during training. They are typically acquired over time by working with experienced pilots during line operations or in many cases after experiencing a problem for the first time and reacting to it in situ, drawing from years of experience to manage the threat. In an attempt to quantify these positive actions, we are proposing an approach to extracting key behaviors within ASRS reports that can support the Safety II concept. Our analysis assumes that ASRS reports contain some descriptions of corrective actions that operators performed to prevent a situation from leading to an accident. Leveraging recent advances in Natural Language Process modeling, we have developed an approach to extract positive sentiment from reports, embed these positive statements in a vector space where they can be numerically analyzed, and clustering these statements into similar contextual categories. From these contextualized categories we can attempt to summarized and distilled aspects of the positive behavior. The goal is to identify categories of behavior that describe consistent operator techniques that supports the Safety II concept. With this information, airlines may enable learning from these positive actions, or address procedures that need to be changed to avoid having pilots implement a workaround. These insights can provide a lens into what is “going right” in the operations that may otherwise not be known widely within the community. It is envisioned that this approach can be extended to other narrative programs such as Line Operation Safety Audit or Learning Improvement Team reports where similar observed behavior can be analyzed to extract positive actions and inform the overall operations.

NLP↗

NASA NTRSDate not supplied

An Approach to Identifying Aspects of Positive Pilot Behavior within the Aviation Safety Reporting System

The National Airspace System (NAS) is constantly evolving as air traffic continues to ramp up to pre-pandemic numbers and projected to grow to unprecedented levels in the coming years. As well as increasing demand to the current system, emerging operations such as Unmanned Autonomous Systems are also expected to add to complexity in the airspace. To address these issues, the industry and government agencies supporting the NAS will need to rely upon additional automation and new technologies to address future operational requirements, while continuing to be a world-leading safe transportation system. As these new technologies are implemented, the system continues to rely on human pilots and controllers in the loop to monitor the system and intervene in situations the automation cannot handle. The goal of proactively addressing safety is of foremost concern to ensure passenger confidence. The industry has implemented various Safety Monitoring Systems to identify safety risks and proactively address them before they result in a serious incident or accident. One such program is the Aviation Safety Reporting System (ASRS). ASRS is a long-established system where pilots and controllers voluntarily and anonymously report safety incidents they experienced and observed during line operations by providing rich text narratives describing the events, the environment, and conditions leading to the safety event of concern. These narratives provide insight and context around events of interest and can be used to identify emerging problems. They can trigger investigations within Flight Operational Quality Assurance or Flight Data Monitoring programs. However, this process typically focuses on the adverse events and the unsafe aspects of the operations surrounding the reported or detected events. This perspective of investigating factors that went wrong around an adverse event is commonly referred to as Safety I. Alternatively, characterizing successful actions that operators perform every day under varying conditions that keep the system within safe operating bounds is a concept referred to as Safety II. The benefit of the Safety II view is that the scope is much larger than that of Safety I since a vast majority of the operations result in successful flights. Many of the successful techniques used to manage operational threats are not documented in standard operating procedures or taught during training. They are typically acquired over time by working with experienced pilots during line operations or in many cases after experiencing a problem for the first time and reacting to it in situ, drawing from years of experience to manage the threat. In an attempt to quantify these positive actions, we are proposing an approach to extracting key behaviors within ASRS reports that can support the Safety II concept. Our analysis assumes that ASRS reports contain some descriptions of corrective actions that operators performed to prevent a situation from leading to an accident. Leveraging recent advances in Natural Language Process modeling, we have developed an approach to extract positive sentiment from reports, embed these positive statements in a vector space where they can be numerically analyzed, and clustering these statements into similar contextual categories. From these contextualized categories we can attempt to summarized and distilled aspects of the positive behavior. The goal is to identify categories of behavior that describe consistent operator techniques that supports the Safety II concept. With this information, airlines may enable learning from these positive actions, or address procedures that need to be changed to avoid having pilots implement a workaround. These insights can provide a lens into what is “going right” in the operations that may otherwise not be known widely within the community. It is envisioned that this approach can be extended to other narrative programs such as Line Operation Safety Audit or Learning Improvement Team reports where similar observed behavior can be analyzed to extract positive actions and inform the overall operations.

NLP↗

NASA NTRSDate not supplied

An Approach to Identifying Aspects of Positive Pilot Behavior within the Aviation Safety Reporting System

The National Airspace System (NAS) is constantly evolving as air traffic continues to ramp up to pre-pandemic numbers and projected to grow to unprecedented levels in the coming years. As well as increasing demand to the current system, emerging operations such as Unmanned Autonomous Systems are also expected to add to complexity in the airspace. To address these issues, the industry and government agencies supporting the NAS will need to rely upon additional automation and new technologies to address future operational requirements, while continuing to be a world-leading safe transportation system. As these new technologies are implemented, the system continues to rely on human pilots and controllers in the loop to monitor the system and intervene in situations the automation cannot handle. The goal of proactively addressing safety is of foremost concern to ensure passenger confidence. The industry has implemented various Safety Monitoring Systems to identify safety risks and proactively address them before they result in a serious incident or accident. One such program is the Aviation Safety Reporting System (ASRS). ASRS is a long-established system where pilots and controllers voluntarily and anonymously report safety incidents they experienced and observed during line operations by providing rich text narratives describing the events, the environment, and conditions leading to the safety event of concern. These narratives provide insight and context around events of interest and can be used to identify emerging problems. They can trigger investigations within Flight Operational Quality Assurance or Flight Data Monitoring programs. However, this process typically focuses on the adverse events and the unsafe aspects of the operations surrounding the reported or detected events. This perspective of investigating factors that went wrong around an adverse event is commonly referred to as Safety I. Alternatively, characterizing successful actions that operators perform every day under varying conditions that keep the system within safe operating bounds is a concept referred to as Safety II. The benefit of the Safety II view is that the scope is much larger than that of Safety I since a vast majority of the operations result in successful flights. Many of the successful techniques used to manage operational threats are not documented in standard operating procedures or taught during training. They are typically acquired over time by working with experienced pilots during line operations or in many cases after experiencing a problem for the first time and reacting to it in situ, drawing from years of experience to manage the threat. In an attempt to quantify these positive actions, we are proposing an approach to extracting key behaviors within ASRS reports that can support the Safety II concept. Our analysis assumes that ASRS reports contain some descriptions of corrective actions that operators performed to prevent a situation from leading to an accident. Leveraging recent advances in Natural Language Process modeling, we have developed an approach to extract positive sentiment from reports, embed these positive statements in a vector space where they can be numerically analyzed, and clustering these statements into similar contextual categories. From these contextualized categories we can attempt to summarized and distilled aspects of the positive behavior. The goal is to identify categories of behavior that describe consistent operator techniques that supports the Safety II concept. With this information, airlines may enable learning from these positive actions, or address procedures that need to be changed to avoid having pilots implement a workaround. These insights can provide a lens into what is “going right” in the operations that may otherwise not be known widely within the community. It is envisioned that this approach can be extended to other narrative programs such as Line Operation Safety Audit or Learning Improvement Team reports where similar observed behavior can be analyzed to extract positive actions and inform the overall operations.

NLP↗

NASA NTRS2014

Usability/Sentiment for the Enterprise and ENTERPRISE

The purpose of the Sentiment of Search Study for NASA Johnson Space Center (JSC) is to gain insight into the intranet search environment. With an initial usability survey, the authors were able to determine a usability score based on the Systems Usability Scale (SUS). Created in 1986, the freely available, well cited, SUS is commonly used to determine user perceptions of a system (in this case the intranet search environment). As with any improvement initiative, one must first examine and document the current reality of the situation. In this scenario, a method was needed to determine the usability of a search interface in addition to the user's perception on how well the search system was providing results. The use of the SUS provided a mechanism to quickly ascertain information in both areas, by adding one additional open-ended question at the end. The first ten questions allowed us to examine the usability of the system, while the last questions informed us on how the users rated the performance of the search results. The final analysis provides us with a better understanding of the current situation and areas to focus on for improvement. The power of search applications to enhance knowledge transfer is indisputable. The performance impact for any user unable to find needed information undermines project lifecycle, resource and scheduling requirements. Ever-increasing complexity of content and the user interface make usability considerations for the intranet, especially for search, a necessity instead of a 'nice-to-have'. Despite these arguments, intranet usability is largely disregarded due to lack of attention beyond the functionality of the infrastructure (White, 2013). The data collected from users of the JSC search system revealed their overall sentiment by means of the widely-known System Usability Scale. Results of the scores suggest 75%, +/-0.04, of the population rank the search system below average. In terms of a grading scaled, this equated to D or lower. It is obvious JSC users are not satisfied with the current situation, however they are eager to provide information and assistance in improving the search system. A majority of the respondents provided feedback on the issues most troubling them. This information will be used to enrich the next phase, root cause analysis and solution creation.

Meza, David↗