Overview of Methods for Computational Text Analysis to Support the Evaluation of Contributions in Public Participation

In this publication in Digital Government: Research and Practice Julia Romberg and Tobias Escher offer a review of the computational techniques that have been used in order to support the evaluation of contributions in public participation processes. Based on a systematic literature review, they assess their performance and offer future research directions.

Abstract

Public sector institutions that consult citizens to inform decision-making face the challenge of evaluating the contributions made by citizens. This evaluation has important democratic implications but at the same time, consumes substantial human resources. However, until now the use of artificial intelligence such as computer-supported text analysis has remained an under-studied solution to this problem. We identify three generic tasks in the evaluation process that could benefit from natural language processing (NLP). Based on a systematic literature search in two databases on computational linguistics and digital government, we provide a detailed review of existing methods and their performance. While some promising approaches exist, for instance to group data thematically and to detect arguments and opinions, we show that there remain important challenges before these could offer any reliable support in practice. These include the quality of results, the applicability to non-English language corpora and making algorithmic models available to practitioners through software. We discuss a number of avenues that future research should pursue that can ultimately lead to solutions for practice. The most promising of these bring in the expertise of human evaluators, for example through active learning approaches or interactive topic modelling.

Key findings

  • There are a number of tasks in the evaluation processes that could be supported through Natural Language Processing (NLP). Broadly speaking, these are i) detecting (near) duplicates, ii) grouping of contributions by topic and iii) analyzing the individual contributions in depth. Most of the literature in this review focused on the automated recognition and analysis of arguments, one particular aspect of the task of in-depth analysis of contribution.
  • We provide a comprehensive overview of the datasets used as well as the algorithms employed and aim to assess their performance. Generally, despite promising results so far the significant advances of NLP techniques in recent years have barely been exploited in this domain.
  • A particular gap is that few applications exist that would enable practitioners to easily apply NLP to their data and reap the benefits of these methods.
  • The manual labelling efforts required for training machine learning models risk any efficiency gains from automation.
  • We suggest a number of fruitful future research avenues, many of which draw upon the expertise of humans, for example through active learning or interactive topic modelling.

Publication

Romberg, Julia; Escher, Tobias (2023): Making Sense of Citizens’ Input through Artificial Intelligence. In: Digital Government: Research and Practice, Artikel 3603254. DOI: 10.1145/3603254.

Mobility Transition through Participation? Policy impact of discursive, consultative public participation on urban transport projects for sustainability

Dissertation Projekt, Laura Mark

In my dissertation project at the Faculty of Architecture at RWTH Aachen University, I am using two case studies to investigate the substantive impact of consultative public participation on political decisions and the implications for sustainable development. My object of investigation is planning for the sustainable mobility transition, since on the one hand it is important and urgent for sustainable development and on the other hand it directly affects people’s everyday lives and thus often leads to resistance.

Abstract

A socio-ecological shift in transport requires profound changes in public space that affect the daily lives of users. This redistribution of road space and change in conditions of use is primarily carried out through spatial planning on the part of the public sector, in which the public is also increasingly involved. This is usually associated (implicitly or explicitly) with the public having an influence on the content of the planning; however, the actual effect has hardly been researched.

I am investigating the mechanisms through which the substantive impact of public participation comes about or is prevented, and which factors influence these mechanisms. I am interested in the conditions under which these substantive effects contribute to integrated transport planning, measured both in terms of democratic theory and substantive criteria.

Two municipal transport transition projects in Hamburg serve as case studies, in which the public can participate or has participated through consultation offers and other forms of participation: the redesign of the Elbchaussee in Hamburg and the low-car design of the Ottensen neighbourhood in Hamburg. The processes differ, among other things, in their framework conditions, spatial scale, tasks and participation offerings. For the detailed reconstruction and analysis of these processes, I mainly rely on data from qualitative interviews, document and media analyses, supplemented by results of quantitative population and participant surveys.

Expected Results

Expected results are theses on public participation in the context of the mobility transition. These deal with the mechanisms and factors that influence policy impact and come about through a detailed analysis of the individual case studies, a targeted comparison of the two case studies with each other and the embedding of the empirical results in the state of research as well as other results from the project. These theses are intended to contribute to the discussion on the role of the public in the context of a socio-ecological transformation.

Supporting the Manual Evaluation Process of Citizen’s Contributions Through Natural Language Processing

Doctoral thesis of Julia Romberg

Engaging citizens in decision-making processes is a widely implemented instrument in democracies. On the one hand, such public participation processes serve the goal of achieving a more informed process and thus to potentially improve the process outcome, i.e. resulting policies, through the ideas and suggestions of the citizens. On the other hand, involving the citizenry is an attempt to increase the public acceptance of decisions made.

As public officials try to evaluate the often large quantities of citizen input, they regularly face challenges due to restricted resources (e.g. lack of personnel,time limitations). When it comes to textual contributions, natural language processing (NLP) offers the opportunity to provide automated support for the evaluation, which to date is still carried out mainly manually. Although some research has already been conducted in this area, important questions have so far been insufficiently addressed or have remained completely unanswered. In my thesis, I have focuses on the sub-tasks of thematic structuring and argument analysis of public participation data.

For the thematic structuring of the contributions, I have chosen a supervised learning approach based on classification algorithms and active learning. On the one hand, I have investigated how much manual effort can be reduced by such strategies, using three case studies from German municipalities as examples (for more insights, please refer to this article). On the other hand, I have developed evaluation metrics that reflect the public analysts’ needs when designing topic classification methods with active learning.

In argument mining, on the one hand, I looked at how robustly argument identification and classification methods perform across different participation processes (for more insights, please refer to this article). On the other hand, I focused on the concreteness of arguments. In addition to predicting a three-level concreteness label, I developed a methodology to take into account the subjectivity of concreteness ratings and their impact on the prediction result (for more insights, please refer to this article).

Enriching Machine Prediction with Subjectivity Using the Example of Argument Concreteness in Public Participation

In this publication in the Workshop on Argument Mining, Julia Romberg develops a method to incorporate human perspectivism in machine prediction. The method is tested on the task of argument concreteness in public participation contributions.

Abstract

Although argumentation can be highly subjective, the common practice with supervised machine learning is to construct and learn from an aggregated ground truth formed from individual judgments by majority voting, averaging, or adjudication. This approach leads to a neglect of individual, but potentially important perspectives and in many cases cannot do justice to the subjective character of the tasks. One solution to this shortcoming are multi-perspective approaches, which have received very little attention in the field of argument mining so far.

In this work we present PerspectifyMe, a method to incorporate perspectivism by enriching a task with subjectivity information from the data annotation process. We exemplify our approach with the use case of classifying argument concreteness, and provide first promising results for the recently published CIMT PartEval Argument Concreteness Corpus.

Key findings

  • Machine learning often assumes a single ground truth to learn from, but this does not hold for subjective tasks.
  • PerspectifyMe is a simple method to incorporate perspectivism in existing machine learning workflows by complementing an aggregated label with a subjectivity score.
  • An example of a subjective task is the classification of the concreteness of an argument (low, medium, high), a task whose solution can also benefit the machine-assisted evaluation of public participation processes.
  • First approaches to classifying the concreteness of arguments (aggregated label) show an accuracy of 0.80 and an F1 value of 0.67.
  • The subjectivity of concreteness perception (objective vs. subjective) can be predicted with an accuracy of 0.72 resp. an F1 value of 0.74.

Publication

Romberg, Julia (2022, October). Is Your Perspective Also My Perspective? Enriching Prediction with Subjectivity. In Proceedings of the 9th Workshop on Argument Mining (pp.115-125), Gyeongju, Republic of Korea. Association for Computational Linguistics. https://aclanthology.org/2022.argmining-1.11

Automated Topic Categorization of Citizens’ Contributions: Reducing Manual Labeling Efforts Through Active Learning

In this publication in Electronic Government, Julia Romberg and Tobias Escher investigate the potential of active learning for reducing the manual labeling efforts in categorizing public participation contributions thematically.

Abstract

Political authorities in democratic countries regularly consult the public on specific issues but subsequently evaluating the contributions requires substantial human resources, often leading to inefficiencies and delays in the decision-making process. Among the solutions proposed is to support human analysts by thematically grouping the contributions through automated means.

While supervised machine learning would naturally lend itself to the task of classifying citizens’ proposal according to certain predefined topics, the amount of training data required is often prohibitive given the idiosyncratic nature of most public participation processes. One potential solution to minimize the amount of training data is the use of active learning. While this semi-supervised procedure has proliferated in recent years, these promising approaches have never been applied to the evaluation of participation contributions.

Therefore we utilize data from online participation processes in three German cities, provide classification baselines and subsequently assess how different active learning strategies can reduce manual labeling efforts while maintaining a good model performance. Our results show not only that supervised machine learning models can reliably classify topic categories for public participation contributions, but that active learning significantly reduces the amount of training data required. This has important implications for the practice of public participation because it dramatically cuts the time required for evaluation from which in particular processes with a larger number of contributions benefit.

Key findings

  • We compare a variety of state-of-the-art approaches for text classification and active learning on a case study of three nearly identical participation processes for cycling infrastructure in the German municipalities of Bonn, Ehrenfeld (a district of Cologne) and Moers.
  • We find that BERT can predict the correct topic(s) for about 77% of the cases.
  • Active learning significantly reduces manual labeling efforts: it was sufficient to manually label 20% to 50% of the datasets to maintain the level of accuracy. Efficiency-improvements grow with the size of the dataset.
  • At the same time, the models operate within an efficient runtime.
  • We therefore hypothesize that active learning should significantly reduce human efforts in most use cases.

Publication

J. Romberg and T. Escher. Automated topic categorisation of citizens’ contributions: Reducing manual labelling efforts through active learning. In M. Janssen, C. Csáki,I. Lindgren, E. Loukis, U. Melin, G. Viale Pereira, M. P. Rodríguez Bolívar, and E. Tambouris, editors,Electronic Government, pages 369–385, Cham, 2022. SpringerInternational Publishing. ISBN 978-3-031-15086-9

Socio-spatial justice through public participation?

In this presentation at the AESOP (Assosiation of European Schools of Planning) annual Congress in 2022, Laura Mark, Katharina Huseljić and Tobias Escher introduced a framework of distributive socio-spatial justice and the way consultation procedures can contribute, before evaluating the case study Elbchaussee in Hamburg regarding socio-spatial justice, using qualitative and quantitative results. 

Abstract

Our current transport system exhibits significant socio-spatial injustices as it has both major negative environmental effects and structurally disadvantages certain socio-economic groups. Planning processes increasingly include elements of public participation, often linked to the hope of better understanding and integrating different mobility needs into the planning process. However, so far there is little knowledge on whether public participation results indeed in more socio-spatial justice.

To approach this question, we focus on socio-spatial justice as distributive justice and investigate how well consultative planning procedures do actually lead to measures that both contribute to sustainability (i.e. reduce or redistribute negative external effects) and cater for the needs of disadvantaged groups (e.g. those with low income or education, women and disabled people). To this end, we have investigated in detail the case study of the reconstruction of the Elbchaussee, a representative main road of citywide importance in the district of Altona in Hamburg, Germany. We are drawing on both qualitative and quantitative data including expert interviews and public surveys.  

We first show that the process did result in planning measures that contribute slightly to ecological sustainability. Second, in particular through improving the situation for pedestrians and cyclists as well as the quality of stay, the measures should contribute to more justice for some groups but this is recognized only by non-male groups. Beyond this there are no effects for people with low income, low education, those with mobility restrictions or with particular mobility needs often associated with these groups. Overall, we conclude that the consultative planning process provides only a small contribution to socio-spatial justice and we discuss potential explanations.

Key Findings

  • The consultative planning process as a whole resulted in measures that contribute slightly to socio-spatial justice, since they support the transition to more sustainable mobility and will benefit some disadvantages groups, though both to a limited degree.
  • We find that the consultation procedure had no significant influence on the policy. In terms of socio-spatial justice, no positive effects can be traced back to the consultation procedure. Notably, those that participated in the consultation did indeed report less satisfaction with the measures.
  • We trace those limited contributions back to some general features of consultation and the current planning system, but also find that in the case study the scope of possible influence was very limited due to external restrictions and power imbalances.

Publication

We are working on a publication for a peer-reviewed journal. The publication will be linked here as soon as it is published.

A Corpus of German Citizen Contributions in Mobility Planning: Supporting Evaluation Through Multidimensional Classification

In this publication in the Conference on Language Resources and Evaluation, Julia Romberg, Laura Mark and Tobias Escher introduce a collection of annotated datasets that promotes the development of machine learning approaches to support the evaluation of public participation contributions.

Abstract

Political authorities in democratic countries regularly consult the public in order to allow citizens to voice their ideas and concerns on specific issues. When trying to evaluate the (often large number of) contributions by the public in order to inform decision-making, authorities regularly face challenges due to restricted resources.

We identify several tasks whose automated support can help in the evaluation of public participation. These are i) the recognition of arguments, more precisely premises and their conclusions, ii) the assessment of the concreteness of arguments, iii) the detection of textual descriptions
of locations in order to assign citizens’ ideas to a spatial location, and iv) the thematic categorization of contributions. To enable future research efforts to develop techniques addressing these four tasks, we introduce the CIMT PartEval Corpus, a new publicly-available German-language corpus that includes several thousand citizen contributions from six mobility-related
planning processes in five German municipalities. The corpus provides annotations for each of these tasks which have not been available in German for the domain of public participation before either at all or in this scope and variety.

Key findings

  • The CIMT PartEval Argument Component Corpus comprises 17,852 sentences from German public participation processes annotated as non-argumentative, premise, or major position.
  • The CIMT PartEval Argument Concreteness Corpus consists of 1,127 argumentative text spans that are annotated according to three levels of concreteness: low, intermediate, and high.
  • Der CIMT PartEval Geographic Location Corpus enthält 4.830 Ortsangaben und die GPS-Koordinaten für 2.529 Beiträge zur Öffentlichkeitsbeteiligung.
  • The CIMT PartEval Thematic Categorization Corpus relies on a new hierarchical categorization scheme for mobility that captures modes of transport (non-motorized transport: cycling, walking, scooters; motorized transport: local public transport, long-distance public transport, commercial transport) and a number of specifications, such as moving or stationary traffic, new services, and inter- and multimodality. In total, 697 documents have been annotated according to this scheme.

Publication

Romberg, Julia; Mark, Laura; Escher, Tobias (2022, June). A Corpus of German Citizen Contributions in Mobility Planning: Supporting Evaluation Through Multidimensional Classification. In Proceedings of the Language Resources and Evaluation Conference (pp. 2874–2883), Marseille, France. European Language Resources Association. https://aclanthology.org/2022.lrec-1.308

Corpus available under

https://github.com/juliaromberg/cimt-argument-mining-dataset

https://github.com/juliaromberg/cimt-argument-concreteness-dataset

https://github.com/juliaromberg/cimt-geographic-location-dataset

https://github.com/juliaromberg/cimt-thematic-categorization-dataset

Robust Methods for Classifying Argument Components in Public Participation Processes for Mobility Planning

In this publication in the Workshop on Argument Mining, Julia Romberg and Stefan Conrad address the robustness of classification algorithms for argument mining to build reliable models that generalize across datasets.

Abstract

Public participation processes allow citizens to engage in municipal decision-making processes by expressing their opinions on specific issues. Municipalities often only have limited resources to analyze a possibly large amount of textual contributions that need to be evaluated in a timely and detailed manner. Automated support for the evaluation is therefore essential, e.g. to analyze arguments.

In this paper, we address (A) the identification of argumentative discourse units and (B) their classification as major position or premise in German public participation processes. The objective of our work is to make argument mining viable for use in municipalities. We compare different argument mining approaches and develop a generic model that can successfully detect argument structures in different datasets of mobility-related urban planning. We introduce a new data corpus comprising five public participation processes. In our evaluation, we achieve high macro F1 scores (0.76 – 0.80 for the identification of argumentative units; 0.86 – 0.93 for their classification) on all datasets. Additionally, we improve previous results for the classification of argumentative units on a similar German online participation dataset.

Key findings

  • We conducted a comprehensive evaluation of machine learning methods across five public participation process in German municipalities that differ in format (online participation platforms and questionnaires) and process subject.
  • BERT surpasses previously published argument mining approaches for public participation processes on German data for both tasks, reaching macro F1 scores of 0.76 – 0.80 for the identification of argumentative units and macro F1 scores of 0.86 – 0.93 for their classification.
  • In a cross-dataset evaluation, BERT models trained on one dataset can recognize argument structures in other public participation datasets (which were not part of the training) with comparable goodness of fit.
  • Such model robustness across datasets is an important step towards the practical application of argument mining in municipalities.

Publication

Romberg, Julia; Conrad, Stefan (2021, November). Citizen Involvement in Urban Planning – How Can Municipalities Be Supported in Evaluating Public Participation Processes for Mobility Transitions?. In Proceedings of the 8th Workshop on Argument Mining (pp. 89-99), Punta Cana, Dominican Republic. Association for Computational Linguistics. https://aclanthology.org/2021.argmining-1.9

Results of the first practical workshop of the junior research group CIMT

Our first practical workshop in summer 2020 focused on the question of how the evaluation of citizen contributions can be technically supported and what requirements practitioners have for a software solution designed to (partially) automate the evaluation.

More information can be found in the working paper (German version only!):