Environmental complaint insights through text mining based on the driver, pressure, state, impact, and response (DPSIR) framework: Evidence from an Italian environmental agency

doi:10.1016/j.regsus.2023.08.002

Abstract

Abstract:

Individuals, local communities, environmental associations, private organizations, and public representatives and bodies may all be aggrieved by environmental problems concerning poor air quality, illegal waste disposal, water contamination, and general pollution. Environmental complaints represent the expressions of dissatisfaction with these issues. As the time-consuming of managing a large number of complaints, text mining may be useful for automatically extracting information on stakeholder priorities and concerns. The paper used text mining and semantic network analysis to crawl relevant keywords about environmental complaints from two online complaint submission systems: online claim submission system of Regional Agency for Prevention, Environment and Energy (Arpae) (“Contact Arpae”); and Arpae's internal platform for environmental pollution (“Environmental incident reporting portal”) in the Emilia-Romagna Region, Italy. We evaluated the total of 2477 records and classified this information based on the claim topic (air pollution, water pollution, noise pollution, waste, odor, soil, weather-climate, sea-coast, and electromagnetic radiation) and geographical distribution. Then, this paper used natural language processing to extract keywords from the dataset, and classified keywords ranking higher in Term Frequency-Inverse Document Frequency (TF-IDF) based on the driver, pressure, state, impact, and response (DPSIR) framework. This study provided a systemic approach to understanding the interaction between people and environment in different geographical contexts and builds sustainable and healthy communities. The results showed that most complaints are from the public and associated with air pollution and odor. Factories (particularly foundries and ceramic industries) and farms are identified as the drivers of environmental issues. Citizen believed that environmental issues mainly affect human well-being. Moreover, the keywords of “odor”, “report”, “request”, “presence”, “municipality”, and “hours” were the most influential and meaningful concepts, as demonstrated by their high degree and betweenness centrality values. Keywords connecting odor (classified as impacts) and air pollution (classified as state) were the most important (such as “odor-burnt plastic” and “odor-acrid”). Complainants perceived odor annoyance as a primary environmental concern, possibly related to two main drivers: “odor-factory” and “odors-farms”. The proposed approach has several theoretical and practical implications: text mining may quickly and efficiently address citizen needs, providing the basis toward automating (even partially) the complaint process; and the DPSIR framework might support the planning and organization of information and the identification of stakeholder concerns and priorities, as well as metrics and indicators for their assessment. Therefore, integration of the DPSIR framework with the text mining of environmental complaints might generate a comprehensive environmental knowledge base as a prerequisite for a wider exploitation of analysis to support decision-making processes and environmental management activities.

Key words: Environmental complaints, Text mining approach, Term Frequency-Inverse Document Frequency (TF-IDF), Driver, pressure, state, impact, and response (DPSIR) framework, Semantic network analysis, Regional Agency for Prevention, Environment and Energy (Arpae)

Fabiana MANSERVISI, Michele BANZI, Tomaso TONELLI, Paolo VERONESI, Susanna RICCI, Damiano DISTANTE, Stefano FARALLI, Giuseppe BORTONE. Environmental complaint insights through text mining based on the driver, pressure, state, impact, and response (DPSIR) framework: Evidence from an Italian environmental agency[J]. Regional Sustainability, 2023, 4(3): 261-281.

Figures/Tables 21

Fig. 1.

Fig. 2.

Table 1

Table 2

Fig. 3.

Fig. 4.

Table 3

Table 4

Table 5

Table 6

Table 7

Table 8

Table 9

Table 10

Table 11

Table 12

Table 13

Table 14

Table 15

Table 16

Table 17

References 68

[1]	Aguwa C., Olya M.H., Monplaisir L., 2017. Modeling of fuzzy-based voice of customer for business decision analytics. Knowledge-Based Syst. 125, 136-145.
[2]	Al-Khouri A.M., 2012. Customer relationship management: Proposed framework from a government perspective times. Journal of Management and Strategy. 3(4), 34-54.
[3]	Arpae (Regional Agency for Prevention, Environment and Energy) Emilia-Romagna, 2022. Fonderie Cooperative di Modena. [2023-06-09]. https://www.arpae.it/it/il-territorio/modena/in-evidenza-a-modena/fonderie-cooperative-di-modena.
[4]	Batagelj A., Mrvar V., 1998. Pajek-program for large network analysis. Connections. 21(2), 47-57.
[5]	Bradley P., 2015. Using the DPSIR Framework to Develop a Conceptual Model: Technical Support Document. [2023-06-09]. https://archive.epa.gov/ged/tutorial/web/html/slide0004-3.html.
[6]	Brewer B., 2007. Citizen or customer? Complaints handling in the public sector. Int. Rev. Adm. Sci. 73(4), 549-556. doi: 10.1177/0020852307083457
[7]	Bruno M.F., Saponieri A., Molfetta M.G., et al., 2020. The DPSIR approach for coastal risk assessment under climate change at regional scale: The case of Apulian Coast (Italy). J. Mar. Sci. Eng. 8, 531, doi: 10.3390/jmse8070531.
[8]	Cañas A.J., Novak J.D., Vanhear J., 2012. Concept Mapping and Environment as a Connection. [2023-06-09]. https://cmc.ihmc.us/cmc2012Papers/cmc2012-p26.pdf.
[9]	Capuano F., de’ Munari E., Forti S., 2018. Il controllo degli odori, nuova frontiera di ricerca. Ecoscienza. 2, 50-51 (in Italian).
[10]	Chen Y.C., 2010. Citizen-centric e-government services: Understanding integrated citizen service information systems. Soc. Sci. Comput. Rev. 28(4), 427-442. doi: 10.1177/0894439309359050
[11]	Cook G.S., Fletcher P.J., Kelble C.R., 2014. Towards marine ecosystem based management in South Florida: investigating the connections among ecosystem pressures, states and services in a complex coastal system. Ecol. Indic. 44, 26-39.
[12]	Cormier R., Kannen A., Elliott M., et al., 2013. Marine and Coastal Ecosystem-Based Risk Management Handbook. Denmark: International Council for the Exploration of the Sea (ICES), 1-60.
[13]	Deidda Gagliardo E., 2002. La Creazione Del Valore Nell’ente Locale. Torino: Giuffrè Publisher (in Italian), 1-456.
[14]	Demsar J., Curk T., Erjavec A., et al., 2013. Orange: Data mining toolbox in Python. The Journal of Machine Learning Research. 14(1), 2349-2353.
[15]	Distante D., Faralli S., Rittinghaus S., et al., 2021. DomainSenticNet: An ontology and a methodology enabling domain-aware sentic computing. Cogn. Comput. 14, 62-77.
[16]	EEA (European Environmental Agency), 2005a. Sustainable Use and Management of Natural Resources. Copenhagen: EEA, 9-11.
[17]	EEA, 2005b. EEA Core Set of Indicators—Guide. Luxembourg: EEA, 1-38.
[18]	EPA (Environmental Protection Agency), 1994. A Conceptual Framework to Support the Development and Use of Environmental Information. Environmental Statistics and Information Division-Making. Washington DC.: United States Environmental Protection Agency, 8-17.
[19]	European Commission, 1999. Towards Environmental Pressure Indicators for the EU (1^st edition). Luxembourg: Office for Official Publications of the European Communities, 1-185.
[20]	European Commission,Directorate-General for Environment, 2020. Environmental Compliance Assurance Vade Mecum. Luxembourg: Publications Office of the European Union, 1-78.
[21]	FAO (Food and Agriculture Organization), 2003. Data Sets, Indicators and Methods to Assess Land Degradation in Drylands. Rome: FAO, 99-102.
[22]	Faralli S., Rittinghaus S., Samsami, et al., 2021. Emotional intensity-based success prediction model for crowdfunded campaigns. Inf. Process. Manag. 58(1), 102394, doi: 10.1016/j.ipm.2020.102394.
[23]	Gabrielsen P., Bosch P., 2003. Environmental Indicators: Typology and Use in Reporting. Copenhagen: European Environmental Agency, 1-20.
[24]	Gebremedhin S., Getahun A., Anteneh W., et al., 2018. A Drivers-Pressure-State-Impact-Responses framework to support the sustainability of fish and fisheries in Lake Tana, Ethiopia. Sustainability. 10, 2957, doi: 10.3390/su10082957.
[25]	Ghodousi M., Alesheikh A.A., Saeidian B., et al., 2019. Evaluating Citizen Satisfaction and Prioritizing Their Needs Based on Citizens’ Complaint Data. Sustainability. 11(17), 4595, doi: 10.3390/su11174595.
[26]	Harris Z., 1954. Distributional structure. Word. 10(23), 146-162. doi: 10.1080/00437956.1954.11659520
[27]	Hartmann S., Mainka A., Stock W.G., 2017. Citizen relationship management in local governments:The potential of 311 for public service delivery. In: Paulin, A., Anthopoulos, L., Reddick, C., (eds.). Beyond Bureaucracy. Public Administration and Information Technology. Berlin:Springer, 337-353.
[28]	ISTAT (Italian national statistical institute), 2023. Resident Population on 1^st January: Emilia-Romagna. [2023-06-17]. https://www.istat.it/en/population-and-households?
[29]	Joung J., Jung K., Ko S., et al., 2019. Customer complaints analysis using text mining and Outcome-Driven Innovation method for market-oriented product development. Sustainability. 11(1), 40, doi: 10.3390/su11010040.
[30]	Kannabiran G., Xavier M.J., Anantharaaj A., 2004. Enabling e-governance through citizen relationship management: Concept, model and applications. Journal of Services Research. 4, 223-240.
[31]	Katir O., Sakalli K., Armutlu H., et al., 2020. Determination of customer satisfaction by text mining: Case of Cappadocia Hotels. Journal of Business Reaearch-Turk. 12, 546-556.
[32]	Khadir A.C., Aliane H., Guessoum A., 2021. Ontology learning: Grand tour and challenges. Comput. Sci. Rev. 39, 100339, doi: 10.1016/j.cosrev.2020.100339.
[33]	Khunanake W., Pradatsudara A., Pattanakiat S., 2018. Stakeholder involvement in developing environmental indicators for the Lam Nam Yang Part 1 Watershed in the Northeastern Thailand. Applied Environmental Research. 40(3), 28-41.
[34]	Larson S., Stone-Jovicich S., 2011. Community perceptions of water quality and current institutional arrangements in the Great Barrier Reef Region of Australia. Water Policy. 13(3), 411-424. doi: 10.2166/wp.2010.084
[35]	Lewison R.L., Rudd M.A., Al-Hayek W., et al., 2016. How the DPSIR framework can be used for structuring problems and facilitating empirical research in coastal systems. Environ. Sci. Policy. 56, 110-119.
[36]	Liu X., Liu H.T., Chen J.C., et al., 2018. Evaluating the sustainability of marine industrial parks based on the DPSIR framework. J. Clean. Prod. 188, 158-170.
[37]	Loomis D.K., Paterson S.K., 2014. Human dimensions indicators of coastal ecosystem services: A hierarchical perspective. Ecol. Indic. 44, 63-68.
[38]	Lucini F.R., Tonetto L.M., Fogliatto F.S., et al., 2020. Text mining approach to explore dimensions of airline customer satisfaction using online customer reviews. J. Air Transp. Manag. 83, doi: 10.1016/j.jairtraman.2019.101760.
[39]	Malekmohammadi B., Jahanishakib F., 2017. Vulnerability assessment of wetland landscape ecosystem services using driver-pressure-state-impact-response (DPSIR) model. Ecol. Indic. 82, 293-303.
[40]	Malmir M., Javadi S., Moridi A., et al., 2021. A new combined framework for sustainable development using the DPSIR approach and numerical modeling. Geosci. Front. 12(4), 260-273.
[41]	Motola V., Colonna N., Alfano V., et al., 2009. Censimento Potenziale Energetico Biomasse, Metodo Indagine, Atlante Biomasse su WEB-GIS. Roma: Italian National Agency for New Technologies, Energy and Sustainable Economic Development (ENEA), 1-140.
[42]	Mozumder M.M.H., Pyhälä A., Wahab M.A., et al., 2019. Understanding social-ecological challenges of a small-scale Hilsa (Tenualosa ilisha) Fishery in Bangladesh. Int. J. Environ. Res. Public Health. 16(23), 4814, doi: 10.3390/ijerph16234814.
[43]	Neshat A., Pradhan B., Dadras M., 2014. Groundwater vulnerability assessment using an improved DRASTIC method in GIS. Resources, Conservation and Recycling. 86, 74-86.
[44]	Niemeijer D.S., de Groot R., 2008. A conceptual framework for selecting environmental indicator sets. Ecol. Indic. 8, 14-25.
[45]	Obubu J., Odong R., Alamerew T., 2022. Application of DPSIR model to identify the drivers and impacts of land use and land cover changes and climate change on land, water, and livelihoods in the L. Kyoga basin: Implications for sustainable management. Environ Syst Res. 11, 11, doi: 10.1186/s40068-022-00254-8.
[46]	OECD (Organisation for Economic Cooperation and Development), 1993. OECD Core Set of Indicators for Environmental Performance Reviews. A Synthesis Report by the Group on the State of the Environment. Paris: OECD Publishing, 5-11.
[47]	OECD, 2005. Integrated Environmental Permitting Guidelines for EECCA Countries. Paris: OECD Publishing, 132-138.
[48]	OECD, 2006. Environment at a Glance:OECD Environmental Indicators. Paris: OECD Publishing, 127-135.
[49]	Patrício J., Elliott M., Mazik K., et al., 2016. DPSIR-Two decades of trying to develop a unifying framework for marine environmental management? Front. Mar. Sci. 3, 177, doi: 10.3389/fmars.2016.00177.
[50]	Rapport D., Friend A., 1979. Towards a Comprehensive Framework for Environmental Statistics:A Stress-Response Approach. Ottawa: Minister of Supply and Services Canada, 27-67.
[51]	Richter P., Cornford J., 2007. Customer relationship management and citizenship: Technologies and identities in public services. Soc. Policy Soc. 7(2), 211-220. doi: 10.1017/S1474746407004162
[52]	Ponte V., 2015. CiRM:CRM no Setor Público. In: Demo, G., (ed.). Marketing de Relacionamento & Comportamento do Consumidor. Atlas: São Paulo, 137-174 (in Portuguese).
[53]	Roche C., 2011. Network analysis of Semantic Web Ontologies. California: Standford University, 13.
[54]	Roy S., Bose A., Majumder S., et al. 2022. Evaluating urban environment quality (UEQ) for Class-I Indian city: an integrated RS-GIS based exploratory spatial analysis. Geocarto International. Doi: 10.1080/10106049.2022.2153932.
[55]	Roy S., Basak D., Bose A., et al. 2023. Citizens’ perception towards landfill exposure and its associated health effects: A PLS-SEM based modeling approach. Environ. Monit. Assess. 195, 134, doi: 10.1007/s10661-022-10722-4.
[56]	Salton G., Buckley C., 1988. Term-weighting approaches in automatic text retrieval. Inf. Process. Manag. 24(5), 513-523. doi: 10.1016/0306-4573(88)90021-0
[57]	Salem M., Bose A., Bashir B., et al., 2021. Urban expansion simulation based on various driving factors using a logistic regression model: Delhi as a case study. Sustainability. 13(19), 10805, doi: 10.3390/su131910805.
[58]	Sami A., Irfan A., Qureshi M.I., et al., 2021. Sustainable public value: A step towards green public organisation for a sustainable society. Int. J. Innov. Sustain. Dev. 15(2), 223-233. doi: 10.1504/IJISD.2021.114330
[59]	Secchi L., 2009. Modelos organizacionais e reformas da administração pública. Revista de Administração Pública. 43(2), 347-369 (in Portuguese). doi: 10.1590/S0034-76122009000200004
[60]	Semeoshenkova V., Newton A., Rojas M., et al., 2017. A combined DPSIR and SAF approach for the adaptive management of beach erosion in Monte Hermoso and Pehuen Co (Argentina). Ocean Coastal Manage. 143, 63-73.
[61]	Smeets E., Weterings R., 1999. Environmental indicators: Typology and overview. Copenhagen: European Environment Agency (EEA), 19.
[62]	Sun C.Z., Wu Y.J., Zou W., et al., 2018. A rural water poverty analysis in China using the DPSIR-PLS model. Water Resour. Manag. 32(6), 1933-1951.
[63]	Sun S.K., Wanga Y.B., Liu J., et al., 2016. Sustainability assessment of regional water resources under the DPSIR framework. J. Hydrol. 532, 140-148.
[64]	Svarstad H., Petersen L.K., Rothman D., et al., 2008. Discursive biases of the environmental research framework DPSIR. Land Use Pol. 25, 116-125.
[65]	Tscherning K., Helming K., Krippner B., et al. 2012. Does research applying the DPSIR framework support decision making? Land Use Pol. 29(1), 102-110. doi: 10.1016/j.landusepol.2011.05.009
[66]	Twizeyimana J.D., Andersson A., 2019. The public value of E-Government-A literature review. Gov. Inf. Q. 36(2), 167-178. doi: 10.1016/j.giq.2019.01.001
[67]	UNEP (United Nations Environment Programme), 1994. World Environment Outlook: Brainstorming Session. [2023-07-17]. https://www.unep.org/events/Environment Assessment Programe.Nairobi.
[68]	Zhan J., Loh H.T., Liu Y., 2009. Gather customer concerns from online product reviews-A text summarization approach. Expert Syst. Appl. 36(2), 2107-2115.

Field	Content
Date	15:04:15 on 24 June 2021
Complaint ID	64890
Province	Modena
Municipality	Maranello
Personal contact information	XXXX
User classification	Private
Claim topic	Odor
Claim content	I cannot open the window because the nearby factory smells like burning rubber at nighttime
Public Relations Office (Italian acronym for “Ufficio Relazioni con il Pubblico (URP) response	Your request has been taken care of by our territorial service and you will be contacted as soon as possible
Response date	09:10:30 on 25 June 2021

Claim topic	Percentage of claim topic to the total environmental complaints (%)
Claim topic	Public	Companies	Local authorities	Citizen associations
Air pollution	32.8	11.3	17.2	25.0
Water pollution	17.5	28.9	21.9	10.0
Noise pollution	16.8	2.6	34.4	20.0
Waste	8.7	10.3	6.2	7.5
Soil	7.4	4.1	3.9	2.5
Generic information	5.4	10.3	2.3	10.0
Electromagnetic radiation	4.3	6.2	12.5	10.0
Odor	4.0	1.5	1.6	10.0
Weather-climate	2.1	12.4	-	5.0
Environmental authorization	0.8	11.9	-	-
Sea-coast	0.2	0.5	-	-
Total	100.0	100.0	100.0	100.0

Complaint topic	Number of environmental complaints
Complaint topic	Bologna	Ferrara	Forlì-Cesena	Modena	Parma	Piacenza	Ravenna	Reggio-Emilia	Rimini	Total
Water pollution	10	6	3	4	7	5	12	6	1	56
Weather-climate	6	4	-	1	1	5	3	4	-	24
Environmental authorization	7	2	3	4	2	2	1	1	1	23
Air pollution	5	1	1	5	-	2	2	5	1	22
Generic information	5	1	3	3	2	1	2	1	2	20
Waste	3	1	2	-	5	1	3	2	3	20
Electromagnetic radiation	-	-	-	-	1	1	1	1	8	12
Soil	1	-	-	2	4	1	1	-	-	8
Noise pollution	1	-	-	2	-	-	-	1	1	5
Odor	-	-	-	3	-	-	-	-	-	3
Sea-coast	1	-	-	-	-	-	-	-	-	1
Total	39	15	12	24	22	18	25	21	19	194

Complaint topic	Number of environmental complaints
Complaint topic	Bologna	Ferrara	Forlì-Cesena	Modena	Parma	Piacenza	Ravenna	Rimini	Total
Noise pollution	1	-	8	1	1	1	8	24	44
Water pollution	6	1	10	2	1	1	2	5	28
Air pollution	1	2	2	-	1	1	3	12	22
Electromagnetic radiation	1	-	5	-	-	-	1	9	16
Waste	1	-	3	1		-	3	-	8
Soil	-	-	2	-	2	-	1	-	5
Generic information	1	-	1	-	-	-	-	1	3
Odor		1	1	-	-	-	-	-	2
Total	11	4	32	4	5	3	18	51	128

Complaint topic	Number of environmental complaints
Complaint topic	Bologna	Ferrara	Forlì-Cesena	Modena	Parma	Piacenza	Ravenna	Reggio-Emilia	Rimini	Total
Air pollution	-	2	1	1	5	-	1	-	-	10
Noise pollution	2	-	2	1	2	-	-	-	1	8
Electromagnetic radiation	2	-	1	-	-	-	-	-	1	4
Generic information	1	2	-	-	-	1	-	-	-	4
Odor	-	-		3	-		-	1	-	4
Water pollution	3	-	1	-	-		-	-	-	4
Waste	1	-	-	-	-	2	-	-	-	3
Weather-climate	1	-	1	-	-	-	-	-	-	2
Soil	-	-	-	-	-	-	-	1	-	1
Total	10	4	6	5	7	3	1	2	2	40