Latent Dirichlet Allocation Topic Model Research Articles

Trend Research on Maritime Autonomous Surface Ships (MASSs) Based on Shipboard Electronics: Focusing on Text Mining and Network Analysis

The growing adoption of electric propulsion systems in Maritime Autonomous Surface Ships (MASSs) necessitates advancements in shipboard electronics for safe, efficient, and reliable operation. These advancements are crucial for tasks such as real-time sensor data processing, control algorithms for autonomous navigation, and robust decision-making capabilities. This study investigates research trends in MASSs, using bibliographic analysis to identify policy and future research directions in this evolving field. We analyze 3363 MASS-related articles from the Web of Science database, employing co-occurrence word analysis and latent Dirichlet allocation (LDA) topic modeling. The findings reveal a rapidly growing field dominated by image recognition research. Keywords such as “datum”, “image”, and “detection” suggest a focus on collecting and analyzing marine data, particularly with deep learning for synthetic aperture radar imagery. LDA confirms this, with “image analysis and classification research” as the leading topic. The study also identifies national and organizational leaders in MASS research. However, research on Arctic routes lags behind that on other areas. This work provides valuable insights for policymakers and researchers, promoting a deeper understanding of MASSs and informing future policy and research agendas regarding the integration of electric propulsion systems within the maritime industry.

Exploring public voice on social media: Twitter Users' views on the circular economy

AbstractThis paper aims to explore all the ideas and topics associated with the discussion about the circular economy on social media sites. All tweets mentioning the CE were collected and subjected to latent Dirichlet allocation topic modelling to identify discussion themes manual validation refined topic coherence. Findings offer novel empirical insights into how the CE is currently framed in public discourse. Dominant themes emphasise strategic communication and technical CE activities rather than inclusive participation. Gaps were also identified, such as limited discussion of CE's social role and broader activities beyond recycling. By quantitatively examining large‐scale online discussions, this research makes an original contribution to establishing the neglected social dimension of CE transitions. The findings carry essential theoretical implications for refining CE conceptualisations better to integrate socio‐cultural factors critical for just, systemic change. Practically, the study equips decision‐makers with data‐driven guidance on developing more participatory communication approaches and policies promoting the CE. This study transitions research and advances the scholarship of the circular economy by using a mixed‐methods approach to analyse a crucial but little‐studied stakeholder perspective.

Renewable energy and sustainable development goals: Insights from latent dirichlet allocation thematic and bibliometric analysis

AbstractThis research conducts a comprehensive analysis of the intricate relationship between renewable energy and the sustainable development goals (SDGs). Employing diverse methodologies including latent dirichlet allocation (LDA) topic modeling, bibliometrics, citation analysis, and regression modeling, the study explores the evolving landscape of renewable energy research and its implications for SDGs. The analysis identifies a pronounced scholarly interest in renewable energy, reflected in the escalating publication volumes and citations across environmental sciences, green technology, and energy studies. Through meticulous examination, it uncovers interconnected research themes; encompassing policy uncertainty, Environmental Kuznets Curve, and ecological footprint, elucidating the multifaceted impact of renewable energy on the SDGs. Geographical distributions underscore diverse regional focuses, emphasizing the need for nuanced, context‐specific approaches. Regression analysis highlights influential factors like carbon dioxide emissions and gross domestic product (GDP) growth, delineating their pivotal roles in shaping scholarly attention toward renewable energy research. Furthermore, the study delves into the economic, environmental, and social dimensions of renewable energy's influence. It reveals its contributions to employment generation, sustainable production, energy access, and infrastructure development while navigating challenges related to climate change mitigation and biodiversity conservation. This comprehensive investigation offers crucial insights into the complex interplay between renewable energy and the SDGs. It predicts future research directions and highlights the urgency for interdisciplinary collaboration, international cooperation, and policy innovations to harness renewable energy's transformative potential for global sustainable development.

Malaysian Chinese folk beliefs on Facebook based on LDA topic modelling

In the digital age, as social media evolves into a new and significant centre for the dissemination of Chinese folk beliefs, the Malaysian Chinese have actively shared information about these folk beliefs on their social media platforms. The dissemination has transcended regional barriers, encouraging more Malaysian Chinese across various states to actively participate in public discussions on this topic. This study delves into Malaysian Chinese folk beliefs by analysing data from Facebook. A comprehensive examination of 4012 text posts was conducted using the latent Dirichlet allocation (LDA) model for topic modelling. The analysis identified four main themes on social media: ‘Practitioners Worship’, ‘Temple Activities’, ‘Deity Legends’, and ‘Merchandise about Deity Statues’. Based on integrating social construction theory and media ecology theory, the study first explores the varied constructors, including practitioners, temple organisations, media organisations, and merchants. Secondly, Malaysian Chinese folk beliefs on social media present characteristics of utilitarianism, regional diversity, multiple social functions, flowing realms, strong Taoist elements, commercialisation, and a close relationship with the Spring Festival. Furthermore, ‘Safety and Peace’, ‘Pray for Demands’, and ‘Merits and Virtues’ form an interconnected semantic nexus. Hence, the findings theoretically highlight the interaction and significance of social media in the construction and practice of folk beliefs within the Malaysian Chinese community. Practically, this research provides valuable insights into the understanding and dissemination of Malaysian Chinese religious culture in the digital era.

Analysis of the Present and Future of the Korea Online Platform Regulation Using Latent Dirichlet Allocation

Purpose: This study was conducted to provide a comprehensive understanding of online platform regulation in South Korea. It aims to illuminate key issues related to online platform regulation from 2017 to 2021, exploring the current state and future prospects. The primary goal is to foster social discourse on online platform regulation and to offer valuable insights for policymakers and academics. Design/methodology/approach: The methodology involved collecting articles from a large news database using keywords associated with online platform regulation. This data was analyzed using Latent Dirichlet Allocation (LDA) topic modeling. This technique is instrumental in identifying themes and patterns within large volumes of text data, facilitating the identification of significant themes and trends related to online platform regulation. Findings: The study unearthed a variety of themes. Among the most significant are the impact of the COVID-19 pandemic and its ramifications, political aspects, the roles of major Korean corporations (e.g., Naver and Kakao), the influence of global tech giants, the impact of news and online communities, technology and innovation, and social issues. These themes indicate that online platform regulation in Korea is influenced by a multitude of factors. Research limitations/implications: While this study offers diverse perspectives on online platform regulation within Korea, it has limitations. Reliance on data from a single news source may restrict the study's diversity and depth. Future research should employ a variety of news sources to provide a broader perspective on online platform regulation. Originality/value: This research makes a significant contribution to the academic study and policy formulation in the field by analyzing the key themes and trends related to online platform regulation over time. By exploring the complex aspects of online platform regulation, the study provides new insights for policymakers, researchers, and the general public.

Standing tall like Caesar? Qatar’s unwavering voice for Palestine at the United Nations

This article examines the complexities of Qatar’s Palestine policy, emphasising Doha’s multifaceted role as a mediator, problem-solver, humanitarian aid provider, and representative of the Palestinian issue at the United Nations. The study employs a mixed-methods research approach. Firstly, it utilises qualitative data from official statements, key policymakers’ remarks, and literature on Qatar’s foreign policy and Palestinian engagement. Secondly, it introduces text analytic methods such as latent Dirichlet allocation (LDA) topic modelling, word clouds and network analysis to identify key themes, relationships and trends in Qatar’s speeches. The findings reveal that the Palestinian issue has been a prominent and consistent topic in Qatar’s United Nations General Assembly General Debate addresses over the past five decades. Qatar has consistently advocated for a resolution to the conflict, emphasising the importance of peace, justice and the two-state solution. Qatar’s support for Palestine remains steadfast, despite pressure from other regional actors to end its engagement with Hamas and divert its attention from the Palestinian issue. This commitment to the Palestinian cause aligns with Qatar’s broader state preferences for an independent foreign policy, its opposition to external interference, and its aspiration to restore its role as a trusted international partner on global platforms.

Assessing the needs of patients with breast cancer and their families across various treatment phases using a Latent Dirichlet Allocation model: a text-mining approach to online health communities.

This study aimed to assess the different needs of patients with breast cancer and their families in online health communities at different treatment phases using a Latent Dirichlet Allocation (LDA) model. Using Python, breast cancer-related posts were collected from two online health communities: patient-to-patient and patient-to-doctor. After data cleaning, eligible posts were categorized based on the treatment phase. Subsequently, an LDA model identifying the distinct need-related topics for each phase of treatment, including data preprocessing and LDA topic modeling, was established. Additionally, the demographic and interactive features of the posts were manually analyzed. We collected 84,043 posts, of which 9504 posts were included after data cleaning. Early diagnosis and rehabilitation treatment phases had the highest and lowest number of posts, respectively. LDA identified 11 topics: three in the initial diagnosis phase and two in each of the remaining treatment phases. The topics included disease outcomes, diagnosis analysis, treatment information, and emotional support in the initial diagnosis phase; surgical options and outcomes, postoperative care, and treatment planning in the perioperative treatment phase; treatment options and costs, side effects management, and disease prognosis assessment in the non-operative treatment phase; diagnosis and treatment options, disease prognosis, and emotional support in the relapse and metastasis treatment phase; and follow-up and recurrence concerns, physical symptoms, and lifestyle adjustments in the rehabilitation treatment phase. The needs of patients with breast cancer and their families differ across various phases of cancer therapy. Therefore, specific information or emotional assistance should be tailored to each phase of treatment based on the unique needs of patients and their families.

Exploring the technology changes of new energy vehicles in China: Evolution and trends

In the sustainable development context, the automotive industry is shifting towards new energy vehicles (NEVs) to reduce carbon emissions. China leads in NEVs production and technology but faces challenges in innovation capacity due to increasing market competition and technological demands. Consequently, to explore the situation of technology innovation of China’s NEVs, this paper delves into the technology changes in this field with the invention granted patents from 2000 to 2021, employing the basic patent-metrics method and Latent Dirichlet Allocation (LDA) topic model for evolution analysis and vector autoregression (VAR) model for trend predictions. The research findings indicate that: (1) the patents pertaining to NEVs have experienced an average annual growth rate of 23%, with notable regional disparities in the spatial distribution of said patents. (2) Among the 8 key technology topics identified, battery equipment technology, brake control system technology, and supplying system technology emerge as the top three technology topics. (3) As NEVs progressively become more intelligent, there is an anticipated surge in interest regarding vehicle braking control technology over the ensuing five years.

Do topic and sentiment matter? Predictive power of online reviews for hotel demand forecasting

Studies integrating textual data for forecasting have mainly focused on the overall sentiment reflected in text. Yet textual data convey various types of information, such as review topics, that can be beneficial when forecasting hotel demand. This study aims to combine topic modeling and sentiment analysis to improve forecasting performance of hotel demand. Specifically, the latent Dirichlet allocation (LDA) topic modeling technique and the long short-term memory (LSTM) model are employed to construct topic-based sentiment indices. The autoregressive integrated moving average (ARIMA) with explanatory variable–type models and mixed data sampling (MIDAS) models are adopted for the evaluation of predictive power. Results reveal that MIDAS forecasting with topic–sentiment and COVID-19 variables generates most accurate forecasts. The findings contextualize the application of online textual big data in hotel demand forecasting research. Hotel management can utilize these online data for short-term forecasting to facilitate crowd management and respond more effectively to unforeseen public health events.

Exploring the connotation of “Local Community” in ICOMOS discourse: a textual analysis based on authoritative documents

As an authoritative institution in cultural heritage conservation, ICOMOS plays a crucial role in guiding local communities’ participation in heritage conservation. However, its scattered and vague descriptions of local communities pose significant obstacles to further research and practice of community participation in heritage conservation. Given the increasing importance of local communities in heritage conservation, it is essential to systematically explore the connotation of Local Community connotations within ICOMOS discourse. This research employs Natural Language Processing methods to analyze ICOMOS’s descriptions of Local Community. Utilizing computational techniques of word frequency calculation, LDA (Latent Dirichlet Allocation) topic model keyword calculation, and hierarchical clustering calculation, the research uncovers relevant keywords and its thematic clusters of Local Community. These findings are further elucidated by aligning them with the principles outlined in authoritative documents of ICOMOS. The research indicates that ICOMOS’s descriptions of Local Community can be summarized into four main keywords families. These keywords families can be summarized as a comprehensive Local Community “three-level, four-family” keywords system. The “Tourism” keywords family exhibits a close association with Local Community, highlighting ICOMOS’s heightened emphasis on heritage tourism. The “Management-Development” keywords family occupies the second level, emphasizing fundamental principles for local communities’ participation in heritage practices. The “Traditional-Knowledge” and “Social-Economic” Keywords Families, situated in the third level, respectively describe the value attributes and conservation approaches of local communities. Each keywords family formed over different periods, exhibiting varying trends of development. By systematically integrating ICOMOS’s descriptions of Local Community and employing Natural Language Processing for in-depth exploration, This research aims to construct a cognitive understanding of local communities from a new perspective of quantitative text analysis, with the intention of providing theoretical references for subsequent research on local communities.

Ranking products through online opinions: A text analysis and regret theory-based approach

With the development of e-shopping, a list of similar products can be found with a large volume of valuable customer reviews online. However, it is generally difficult to compare various aspects of similar products effectively by understanding all relevant online opinions. To help consumers, in this study, how products are ranked according to online reviews is investigated. Firstly, an SC-LDA (Seed Constraint-Latent Dirichlet Allocation) model, which is an extension of the classical topic model LDA (Latent Dirichlet Allocation), is proposed to extract product features. The must-link and cannot-link seed constraints are invited to estimate the probability expansion/reduction value. They help to affect the topic allocation by additional constraints in Gibbs sampling for a higher accuracy on feature extraction. Secondly, an improved convolutional memory neural network model is devised to analyze the sentiment polarity. It takes the advantages of CNN (convolutional neural network) and Bi-LSTM (bidirectional Long Short-Term Memory) and performs dynamic pooling in CNN to prevent the loss of important features. Besides, the concept of group satisfaction degree is introduced, which makes products be compared according to the Regret Theory. It ranks products without a commonly applied reference point and take consumer psychology into considerations. Finally, in the case study, an illustrative example is presented to evaluate the proposed framework. Categories of experiments show that the proposed framework provides consumers with effective purchase suggestions. Code metadataPermanent link to reproducible Capsule: https://doi.org/10.24433/CO.6445683.v1 and https://doi.org/10.24433/CO.2658577.v1.

Evolution of renewable energy laws and policies in China

This study employs Latent Dirichlet Allocation (LDA) topic modelling methodology to analyze documents related to renewable energy laws and policies at the central level in China. The objective is to investigate the development and evolution of renewable energy policies in China and to gain insights into the national-level attitudes towards renewable energy development. The study consists of two phases: initially, renewable energy policy documents undergo keyword analysis using word clouds and keyword co-occurrence network analysis to elucidate the focal areas and their interconnections within the legal and policy texts. Subsequently, after determining the optimal number of topics for modelling based on topic perplexity and consistency results, the text undergoes data cleaning to isolate words with practical significance. These words are then incorporated into the LDA topic model to analyze the distribution and content of potential topics within the policies. Lastly, by linearly segmenting the time frame, changes in topic intensity over time are visually examined using heat maps. The findings indicate that energy policies have consistently prioritized “development” and emphasized the significance of “new energy” in renewable energy policies. Moreover, as renewable energy has progressed, governments and policymakers have come to acknowledge the importance of comprehensive energy planning, transitioning to clean energy sources, and regulating the electricity market. This growing awareness has led to efforts to strengthen policy and regulatory measures to foster renewable energy's sustainable development and utilization. In summary, this study highlights the effectiveness of the LDA topic model in analyzing renewable energy policies, advancing its adoption and furthering research in the field.

데이터로 본 판소리의 性 인지 체계: 신재효本을 중심으로

This study analyzes the sexual cognitive system in pansori works using Shin Jae-hyo’s pansori texts as the research subject. To that end, I first extracted excerpts of sexual expressions from Shin Jae-hyo’s pansori texts such as Chunhyang-ga(NamChang), Simcheong-ga, Bak-Taryeong, Tobyol-ga, Jeokbyeok-ga, and Byeongangsoe-ga. Then, I input them on a sentence-by-sentence basis with metadata including the speaker (narrator), target of description, related characters, works, and excerpts. As a preliminary step for the quantitative analysis, I performed morphological analysis and preprocessing on the data entered in the text column. This made the language of the pansori texts suitable for digital analysis tools with the input of new information or stop words into the user dictionary.
 Three analyses were attempted using the data extracted from Shin Jae-hyo’s pansori texts. First, basic statistical analysis was conducted to visualize which work had the most occurrences of sexual expressions and to examine the frequency of speaker-description target pairs when sexual expressions were uttered and their targets. Second, Latent Dirichlet Allocation (LDA) topic modeling was performed to extract topics from a large collection of documents. Third, I used co-occurrence word analysis to reveal the semantic network of words constituting sexual expressions.
 The findings revealed that the sexual cognitive system in pansori works is based on “deviation and return.” That is, while enjoying pansori, one can realize that forbidden desires are, indeed, common desires and can satisfy sexual fantasies. However, such desires should not persist beyond exceptional circumstances and should ultimately be concealed and transformed to abide byto societal norms. Listening to and reading pansori involves repeatedly deviating from and returning to sexuality as a theme that persists throughout the whole story.

Decoding paradoxical identities: The discourse construction of left-behind children in news reports

This paper presents an empirical corpus-based study on the identity of left-behind children in China, employing the discourse-historical approach (DHA) framework. It is the first study to combine Latent Dirichlet Allocation (LDA) topic modeling and reported speech analysis to examine how China Daily constructs the identity of left-behind children and explore the cultural and rhetorical factors influencing this identity construction. By integrating computational techniques and qualitative analysis methods, this study provides a comprehensive understanding of the intricate nature of identity construction for left-behind children. This interdisciplinary approach strengthens the theoretical foundations of media analysis and offers fresh insights into the dynamics of media discourse. The findings reveal that China Daily portrays left-behind children in a multifaceted and diverse manner, encompassing both positive and negative aspects, while placing emphasis on their vulnerability and passivity. Furthermore, the media employs communication techniques such as identification by sympathy, antithesis, and inaccuracy to establish emotional resonance and foster audience identification, ultimately influencing the audience’s perspectives on these children.

잠복결핵에 관한 온라인 건강 상담 현황

The study’s objective is to explore the health information needs of latent tuberculosis patients and their communities by analyzing data from the online health counselling platform, Naver Jisik-iN. Initially, 3,261 questions related to ‘latent tuberculosis’ were collected. Following the removal of duplicates and irrelevant image information, the final dataset for analysis comprised 2,198 questions. Text pre-processing, Latent Dirichlet Allocation (LDA) topic modelling, and Long Short-Term Memory (LSTM)-based text summarization model were used. Manual categorization was added to supplement the unsupervised learning process. Seven topics were identified using LDA, from which five specific topics (‘side effects’, ‘treatment’, ‘army’, ‘interaction’, and ‘infectiousness’) were derived. Subsequently, manual classification was conducted based on these five topics. Manual summary and LSTM-based text summarization results were consistent. Numerous individuals sought information about the potential for curing latent tuberculosis and the risk of tuberculosis development. Moreover, questions related to the interpretation of test results and interactions with other substances were widespread. Concerning side effects, issues predominantly revolved around drug discontinuation due to skin problems and elevated liver function tests. The findings reveal the prevalent concerns and inquiries of society regarding latent tuberculosis. The identified topics offer valuable insights into the key aspects of interest related to this condition.

Analysis of Suicide-related Tweets During the COVID-19 Pandemic

Background:: The COVID-19 virus started in 2019 and badly affected the different sectors of many countries around the world. Based on this, financial difficulties, loss of loved ones, sudden anger, relationships, family disputes, and psychological distress increased, and individuals were stalled from carrying out their lifestyle in a normal way, and some individuals were even motivated to commit suicide. Objective:: It is important to reduce the number of suicides and identify the reasons for this situation. Through this research, the focus is on identifying the main topics discussed relevant to suicides during the COVID-19 pandemic. Methods:: Individuals use Twitter, a social media platform, to share their ideas freely and publically. We collected 9750 primary data through Twitter API (Application Programming Interface). After preprocessing and feature extraction by TF-IDF (Term Frequency-Inverse Document Frequency), we applied the LDA (Latent Dirichlet Allocation) and Probabilistic Latent Semantic Analysis (PLSA) topic modeling algorithms to identify topics. Results:: Based on the LDA results, we extracted ten different topics under the three themes, such as the impact of COVID-19, human feelings, getting support, and having awareness. Intertopic Distance Map, Most Salient Terms, and Word Clouds Visualization are used to check the results. The coherence score and perplexing value are used to measure how interpretable the extracted topics are to humans. PLSA also extracted 25 topics with their probabilities, and Kullback–Leibler (KL) divergence was used to check the results. Conclusion:: We were able to gain insight into human emotions and the main motivations behind suicide attempts using the topics we extracted. Expert feedback proved that LDA results were better than PLSA. Based on that, we found the main impact of COVID-19 on human lives, how human feelings were changed positively and negatively during that period, what supporting and awareness methods people used, and what they preferred. The required measures can then be taken by those responsible authorities and individuals to prevent, reduce, and get ready for this kind of suicidal incident in the future.

“Those blimmin Ts and Cs”: a mixed methods analysis of how people manage personal information, privacy, and impressions

ABSTRACT Interconnected and smart technologies complicate personal information management (PIM) because users delegate the storing, organizing, and retrieving of personal information to smart and mobile service providers. Meta-level PIM activities are required to maintain the privacy and security of personal information. This study provides insights into how users of location tracking, mobile apps, and smart home technologies perceive PIM and privacy. We turn to the privacy as contextual integrity (CI) and impression management (IM) literatures to explore informational norms and interpersonal dynamics in PIM. This study is based on a mixed methods design to analyze focus groups and interviews with 106 British and Dutch respondents. Combining unsupervised Latent Dirichlet allocation (LDA) topic modeling and thematic analysis, we reveal discursive patterns in respondent accounts of technology use and provide an in-depth interpretation of these patterns. Our findings indicate that PIM practices are associated with the perceived appropriateness of information flows, anthropomorphic interpretations of technologies, and interpersonal surveillance. Thus, impressions are managed toward social actors as well as technology providers. We contribute to PIM research with a demonstration of how PIM in mobile, smart, and location-based technology use cannot be separated from contextual factors and strategies to manage impressions of habits and behaviors.

Evaluation and Analysis of Synergy between Energy and Environmental Policies in Coal Resource-Rich Areas

The policy synergy of coal resource-rich areas directly affects the process of regional green transformation and high-quality development. Shanxi, Shaanxi and Inner Mongolia are important coal energy bases, and studying the energy and environmental policies of these three provinces is of great significance to sustainable development. Using social network analysis, the Latent Dirichlet Allocation (LDA) topic model and textual similarity methods, we conducted a synergistic study of policy issuance subjects and policy text contents of Shanxi, Shaanxi and Inner Mongolia from both horizontal and vertical perspectives. The results show that: (1) in the policy subject dimension, Shanxi had the highest degree of synergy, but overall the synergy in all three provinces was insufficient, and the number of multi-subject joint texts was relatively small; (2) in the policy content dimension, the textual similarity and goal consistency between Inner Mongolia and the Central Government were better than that of Shaanxi and Shanxi. Therefore, the region of “Shanxi–Shaanxi–Inner Mongolia” should improve the synergistic ability of policy issuance subjects; it should also pay attention to the linkage and refinement of the policy content, and make flexible innovations based on the compatibility with the Central policy incentives, to better promote the low-carbon and green transformation of coal resource-rich areas.

Enhancing infrastructural dynamic responses to critical residents’ needs for urban resilience through machine learning and hypernetwork analysis

The increasing frequency of extreme weather events poses ever greater challenges to urban resilience and residents’ quality of life. Despite a growing trend advocating for an anthropocentric approach to urban resilience, there remains an inadequate understanding of the evolving hierarchical needs of residents during post-disaster periods, especially considering the interplay with infrastructure service restoration. This study aims to address the gap by elucidating how emergency governance and urban infrastructure repairs can effectively address critical residents’ needs, providing empirical insights for improved resource allocation in infrastructure rush-repair scenarios. First, we categorize residents’ needs into three layers (safety and health, social livelihood and civic engagement) using Latent Dirichlet Allocation topic modeling. Subsequently, we present an urban resilience assessment framework that traces the recovery of residents’ needs alongside dynamic infrastructural functionality restoration, benchmarking against pre-disaster levels. Additionally, hypernetwork analyses are adopted to identify critical and evolving patterns of residents’ post-disaster needs over time. The robustness of our proposed framework is validated through its application to a dataset comprising 220,567 records from residents’ appeals during three recurrent rainfall events in Beijing. Theoretically, this study models the dynamic interactions between residents’ needs and infrastructure response during urban post-disaster recovery. Practically, the pinpointed critical needs guide efficient infrastructure rush-repairs and proactive disaster prevention in infrastructure maintenance.

Deciphering Public Voices in the Digital Era

Problem, research strategy, and findings Planners are increasingly using online public engagement approaches to broaden their reach in communities. This results in substantial volumes of digital, text-based public feedback data, making it difficult to analyze efficiently and derive meaningful insights. We explored the use of the novel large language model (LLM), ChatGPT, in analyzing a public feedback data set collected via online submissions in Hamilton City (New Zealand) in response to a proposed local plan change. Specifically, we initially employed zero-shot prompts with ChatGPT for tasks like summarizing, topic identification, and sentiment analysis and compared the results with those obtained by human planners and two standard natural language processing (NLP) techniques: latent Dirichlet allocation (LDA) topic modeling and lexicon-based sentiment analysis. The findings show that zero-shot prompting effectively identified political stances (accuracy: 81.7%), reasons (87.3%), decisions sought (85.8%), and associated sentiments (94.1%). Although subject to several limitations, ChatGPT demonstrates promise in automating the analysis of public feedback, offering substantial time and cost savings. In addition, few-shot prompting enhanced performance in more complex tasks, such as topic identification involving planning jargon. We also provide insights for urban planners to better harness the power of ChatGPT to analyze citizen feedback. Takeaway for practice ChatGPT presents a transformative opportunity for planners, particularly those dealing with growing volumes of public feedback data. However, it cannot be entirely relied upon. Planners must be mindful of ChatGPT’s limitations, including its sensitivity to prompt phrasing, inherent biases from training data, tendency to overgeneralize, and occasional omission of nuanced details. To enhance accuracy, planners should prescreen data for consistency, provide clear and iteratively tested prompts, use few-shot prompts for complex analysis, and explore various combinations of prompting strategies to develop an effective local approach. It is also crucial to ensure human review of the results.