Semantic Analysis Tool Research Articles

Comparative Evaluation of Keyphrase Extraction Tools for Semantic Analysis of Climate Change Scientific Reports and Ontology Enrichment

Comparative Evaluation of Keyphrase Extraction Tools for Semantic Analysis of Climate Change Scientific Reports and Ontology Enrichment

A Survey on the Media Information Flow to Contribute Bulgaria’s Destination Image and Perception

Travel and tourism business has proved to be powerful accelerator and contributor to the global economy. As a flexible and highly adaptive to many disruptive events industry, it has been handling crises of various nature, origin and background. The current publication is focused on the role the media information flow exerts on to the image and perception of destination Bulgaria. The survey aims to perform a quality analysis of the news published and announced by leading media broadcasts and to evaluate their influence when making a decision to undertake travel. The study period is limited to the 2023 summer season. For the purposes of the survey, Web service tool for semantic analysis is implemented. In the course of the research, it is revealed that negative news related to tourism prevails and this could have a negative impact on the destination.

Exploring the terminological validity of 'chronic pain' nursing diagnosis: A retrospective descriptive study using nursing diaries.

The aim of this study is to generate empirical evidence, drawing from clinical records, with the goal of elevating the level of evidence supporting the nursing diagnosis (ND) of 'chronic pain'. Chronic pain is a prevalent condition that affects all age groups. Patients often feel disbelieved about their pain perception, leading to adverse psychological effects, difficulty accessing healthcare and poor rehabilitation outcomes. Retrospective descriptive study. Standards for Reporting Diagnostic Accuracy Studies guidelines were followed in this study. Data were extracted from Electronic Health Records (EHR) of patients admitted to the University Hospital of Perugia, Italy, between March 2016 and December 2022. The study sample comprised individuals without a specific medical diagnosis or high-risk population. Out of 1,048,565 EHR, 43,341 clinical-nursing diaries with the keyword 'pain' were identified, from which 283 clinical-nursing notes were selected based on a keyword-based retrieval technique and diagnostic definition for further analysis. Our study findings support the diagnostic descriptors of the 'chronic pain' ND in clinical-nursing diaries. We observed the presence of 9 out of 11 defining characteristics, 7 out of 10 related factors, 4 out of 8 at-risk populations and 11 out of 17 associated conditions. The study validated diagnostic criteria for chronic pain and proposed 'haematological pathology' as a new associated condition. The findings were presented to the Diagnosis Development Committee of NANDA-International for further review. However, limitations of the study prompted the need for further analysis using natural language processing and artificial neural network techniques. As a result, a new research direction using artificial intelligence (AI) tools was initiated. The study validates diagnostic descriptors for chronic pain and proposes future directions in semantic analysis and AI tools, aiming to enhance clinical practice and decision-making in nursing care. No patient or public contribution.

Mistrz. Krtka historia sowa w polszczynie (badania korpusowe)

In this article, I analysed the history of the occurrence of one lexeme in Polish in the last 200 years: master (pol. mistrz). With data from Polish language corpora, I traced its frequency and examined its semantics and its transformations. Corpus analyses confirmed the semantic shifts taking place from the meaning of teacher, guide to the meaning of sport; also revealed a new ironic semantic shade of the analysed word. The second aim of the article was to develop postulates for corpus-based semantic research. These are: firstly, semantic analyses should be carried out on relatively small corpora; secondly, there is an urgent need to develop a (semi-)automatic tool for semantic analysis on corpus data (the linguistic basis for computer science work in this direction can be found here in the mental dictionary of A. Wierzbicka).

Mapping the leap: differences in quality improvement in relation to assessment rating outcomes

IntroductionAustralia’s National Quality Standard (NQS) outlines the criteria to assess the quality of early childhood services. A four-point rating scale: (i) Exceeding NQS; (ii) Meeting NQS; (iii) Working Toward NQS; and (iv) Significant Improvement Required is applied to services following a regular assessment and rating process. Settings rated as Working Toward are reassessed within 12 months. Most settings achieved a one-step improvement in this Time 2 reassessment, moving to a Meeting rating but some settings made a two-step improvement, moving to an Exceeding rating. The QIP is a key document used by authorities to assess the quality of a service.MethodsA grounded theory, data driven approach was taken to deepen understanding of quality rating improvements in long day care services in Australia of quality rating improvements by early childhood education and care [ECEC] services in Australia. This study, part of the second phase of a three phase study involved a document analysis of the Time 2 Quality Improvement Plans (QIPs) of a representative sample of Long Day Care (LDC) services (n = 60) from all Australian states and territories to determine what factors may have contributed to these different levels of improvement, with a focus on Quality Area 1 (QA1) (Educational programs and practices) and Quality Area 7 (QA7) (Governance and leadership). The study utilized the semantic analysis tool Leximancer 4.5. Leximancer 4.5 statistically analyses the semantic relationships between concepts in documents by measuring word proximity and correlation. The software creates visual maps of concepts and their connections to each other in texts. Concepts located near one another on the map are more likely to be contextually related. This tool is particularly useful when there are multiple, complex documents to analyze, reducing the potential biases that can arise from documents that use language with which these researchers are very familiar with.ResultsThe analysis found clear differences between the Time 2 QIPs of services who had made a two-step rating improvement and those who made a one-step improvement. Two-step (Exceeding NQS) category improvers for QA1 placed attention in their QIPs on improvement to the program and overall practice, with an orientation to the role of the educational leader. Two-step (Exceeding NQS) category improvers for QA7 seemed to be more oriented to a systemic view of the processes encompassed by QA7; how the management of the service and information supports the work of educators, with stronger links made between leadership roles (the manager and nominated supervisor) and the work of educators.DiscussionThe QIPs demonstrated how the intentional and systemic processes in these quality areas related to practice, management, and leadership.

Создание средств интеллектуальной поддержки процедур рекрутинга инновационного предприятия на основе методов обработки естественного языка

When conducting recruiting procedures for a modern innovative company, the task of creating automated solutions designed to objectively determine the competencies of an employee is most urgent. There have been de-scribed the results of an analytical review of methods that allow identifying the competencies of specialists based on semantic studies of texts generated by them, followed by analysis of the applicability of such solutions to perform specific recruiting procedures. There is given a description of an approach to creating collections of texts characterizing the competencies of the applicant for the vacancy, which are classified according to the time of text generation (retrospective experience /current activity) and interaction with co-authors. There have been considered the examples of using different methods of Natural language processing based on the vector representation of texts for solving specific tasks related to the assessment of the competencies of specialists and the tools for semantic analysis of texts.

Semantic Analyses of Open-Ended Responses From Professional Development Workshop Promoting Computational Thinking in Rural Schools

The development of curriculum and access to educational resources related to applied computing is lacking for students in K-12 schools particularly in rural areas, despite the large and growing demand for computing skills in the job market. Motivated by this need, an interdisciplinary professional development workshop was designed to promote computational thinking and curriculum integration among teachers involved in teaching core curricula including writing, math, science, and social studies in grades 3-8 in a rural midwestern state in the USA, as part of a longitudinal grant-funded program. Open-text feedback was collected before, during, and immediately after the workshop in response to multiple types of formative assessments. In this paper, we present several forms of data representation from exploratory textual analyses based on the feedback collected from the workshop participants. Semantic analysis tools including sentiment analysis and thematic analysis facilitated the identification of common themes in perception among grade 3-8 teachers relating to the implementation of computational concepts in their classrooms. Results suggest that these techniques can be useful in evaluating open-ended feedback to represent patterns of response which may aid in the identification of actionable insights related to adult learner perceptions, including interest and self-efficacy.

Android-IoT Malware Classification and Detection Approach Using Deep URL Features Analysis

Currently, malware attacks pose a high risk to compromise the security of Android-IoT apps. These threats have the potential to steal critical information, causing economic, social, and financial harm. Because of their constant availability on the network, Android apps are easily attacked by URL-based traffic. In this paper, an Android malware classification and detection approach using deep and broad URL feature mining is proposed. This study entails the development of a novel traffic data preprocessing and transformation method that can detect malicious apps using network traffic analysis. The encrypted URL-based traffic is mined to decrypt the transmitted data. To extract the sequenced features, the N-gram analysis method is used, and afterward, the singular value decomposition (SVD) method is utilized to reduce the features while preserving the actual semantics. The latent features are extracted using the latent semantic analysis tool. Finally, CNN-LSTM, a multi-view deep learning approach, is designed for effective malware classification and detection.

Text mining for social science – The state and the future of computational text analysis in sociology

The emergence of big data and computational tools has introduced new possibilities for using large-scale textual sources in sociological research. Recent work in sociology of culture, science, and economic sociology has shown how computational text analysis can be used in theory building and testing. This review starts with an introduction of the history of computer-assisted text analysis in sociology and then proceeds to discuss five families of computational methods used in contemporary research. Using exemplary studies, it shows how dictionary methods, semantic and network analysis tools, language models, unsupervised, and supervised machine learning can assist sociologists with different analytical tasks. After presenting recent methodological developments, this review summarizes several important implications of using large datasets and computational methods to infer complex meaning in texts. Finally, it calls researchers from different methodological traditions to adopt text mining tools while remaining mindful of lessons learned from working with conventional data and methods.

Извлечение информации об использовании информационных технологий для поддержки принятия решений в медицинской диагностике

The use of information technology in medical practice radically changes the formulation, methods and means of solving most practical problems. The transition to modern information technologies provides new opportunities and improves the quality of service, reduces examination time, increases diagnostic accura-cy, etc. Purpose of the study. Extraction of information about the use of information technology for deci-sion support in medical diagnostics based on the analysis of publications in this field. Materials and meth-ods. For a formal representation of the process of structural-semantic analysis\ of information on the use of IT in medicine, a functional model was built in the IDEF0 notation. When conduc¬ting research in a spe-cific subject area, an analysis of known scientific results and practical solutions is required, for which scien-tific publications posted in various sources are used. There are platforms where information about such da-ta is collected, allowing to determine the quantitative indicators of the publication, their specific character-istics, etc. Semantic analysis tools were used to identify the dynamics of the appea¬rance of publications; to make comparative analysis of the effectiveness of various scientists and research organizations; to deter-mine publishing activity in the journal sector. To determine the features of publishing activity, an addition-al analysis was conducted by the analyst, who is a specialist in semantic analysis. Statistical analysis methods were used to process the collected information. Since a small amount of data has been collected, there is no need to use specialized analysis tools, and Excel tools were used to build charts. Results. The key characteristics of publications on the analyzed topic, the dynamics of the appearance of articles, the most active authors, scientific schools and the most popular journals in which the research results are published are identified. The results of extracting information about research in the field of IT use in cardiology from the most popular publications of active authors are presented. Conclusion. The analysis of publications based on the data of the elibrary.ru platform is a preliminary stage in the study of scientific texts on a se-lected research topic. For the future research, it is necessary to develop an information system to support researchers with complex indicators and data based on the analysis of scientific texts.

Can MOOC Instructor Be Portrayed by Semantic Features? Using Discourse and Clustering Analysis to Identify Lecture-Style of Instructors in MOOCs

Nowadays, most courses in massive open online course (MOOC) platforms are xMOOCs, which are based on the traditional instruction-driven principle. Course lecture is still the key component of the course. Thus, analyzing lectures of the instructors of xMOOCs would be helpful to evaluate the course quality and provide feedback to instructors and researchers. The current study aimed to portray the lecture styles of instructors in MOOCs from the perspective of natural language processing. Specifically, 129 course transcripts were downloaded from two major MOOC platforms. Two semantic analysis tools (linguistic inquiry and word count and Coh-Metrix) were used to extract semantic features including self-reference, tone, effect, cognitive words, cohesion, complex words, and sentence length. On the basis of the comments of students, course video review, and the results of cluster analysis, we found four different lecture styles: “perfect,” “communicative,” “balanced,” and “serious.” Significant differences were found between the different lecture styles within different disciplines for notes taking, discussion posts, and overall course satisfaction. Future studies could use fine-grained log data to verify the results of our study and explore how to use the results of natural language processing to improve the lecture of instructors in both MOOCs and traditional classes.

A Semi-Automatic Methodology for Making FMEA Surveys

This paper proposes a semi-automatic methodology to assist the user in creating surveys about FMEA and Risk Analysis, based on a customized use of the tools for semantic analysis and in particular a home-developed syntactic parser called Kompat Cognitive. The core of this work has been the analysis of the specific FMEA-related jargon and its common modalities of description within scientific papers and patents in order to systematize the linguistic analysis of the reference documents within the proposed step-divided procedure. The main goals of the methodology are to assist not skilled in the art users about FMEA during the analysis of generic and specific features, by considering large moles of contributions in restricted amounts of time. The methodology has then been tested on the same pool of 286 documents, divided between 177 and 109 patents, manually analyzed in our previous survey, in order to replicate part of its classifications through the proposed new modality. In this way we evaluated the abilities of the methodology both to automatically suggesting the main features of interest and to classify the documents according to them.

Relationship among subjective responses, flavor, and chemical composition across more than 800 commercial cannabis varieties

BackgroundWidespread commercialization of cannabis has led to the introduction of brand names based on users’ subjective experience of psychological effects and flavors, but this process has occurred in the absence of agreed standards. The objective of this work was to leverage information extracted from large databases to evaluate the consistency and validity of these subjective reports, and to determine their correlation with the reported cultivars and with estimates of their chemical composition (delta-9-THC, CBD, terpenes).MethodsWe analyzed a large publicly available dataset extracted from Leafly.com where users freely reported their experiences with cannabis cultivars, including different subjective effects and flavour associations. This analysis was complemented with information on the chemical composition of a subset of the cultivars extracted from Psilabs.org. The structure of this dataset was investigated using network analysis applied to the pairwise similarities between reported subjective effects and/or chemical compositions. Random forest classifiers were used to evaluate whether reports of flavours and subjective effects could identify the labelled species cultivar. We applied Natural Language Processing (NLP) tools to free narratives written by the users to validate the subjective effect and flavour tags. Finally, we explored the relationship between terpenoid content, cannabinoid composition and subjective reports in a subset of the cultivars.ResultsMachine learning classifiers distinguished between species tags given by “Cannabis sativa” and “Cannabis indica” based on the reported flavours: <AUC> = 0.828 ± 0.002 (p < 0.001); and effects: <AUC> = 0.9965 ± 0.0002 (p < 0.001). A significant relationship between terpene and cannabinoid content was suggested by positive correlations between subjective effect and flavour tags (p < 0.05, False-Discovery-rate (FDR)-corrected); these correlations clustered the reported effects into three groups that represented unpleasant, stimulant and soothing effects. The use of predefined tags was validated by applying latent semantic analysis tools to unstructured written reviews, also providing breed-specific topics consistent with their purported subjective effects. Terpene profiles matched the perceptual characterizations made by the users, particularly for the terpene-flavours graph (Q = 0.324).ConclusionsOur work represents the first data-driven synthesis of self-reported and chemical information in a large number of cannabis cultivars. Since terpene content is robustly inherited and less influenced by environmental factors, flavour perception could represent a reliable marker to indirectly characterize the psychoactive effects of cannabis. Our novel methodology helps meet demands for reliable cultivar characterization in the context of an ever-growing market for medicinal and recreational cannabis.

UFO: A tool for unifying biomedical ontology-based semantic similarity calculation, enrichment analysis and visualization.

BackgroundBiomedical ontologies have been growing quickly and proven to be useful in many biomedical applications. Important applications of those data include estimating the functional similarity between ontology terms and between annotated biomedical entities, analyzing enrichment for a set of biomedical entities. Many semantic similarity calculation and enrichment analysis methods have been proposed for such applications. Also, a number of tools implementing the methods have been developed on different platforms. However, these tools have implemented a small number of the semantic similarity calculation and enrichment analysis methods for a certain type of biomedical ontology. Note that the methods can be applied to all types of biomedical ontologies. More importantly, each method can be dominant in different applications; thus, users have more choice with more number of methods implemented in tools. Also, more functions would facilitate their task with ontology.ResultsIn this study, we developed a Cytoscape app, named UFO, which unifies most of the semantic similarity measures for between-term and between-entity similarity calculation for all types of biomedical ontologies in OBO format. Based on the similarity calculation, UFO can calculate the similarity between two sets of entities and weigh imported entity networks as well as generate functional similarity networks. Besides, it can perform enrichment analysis of a set of entities by different methods. Moreover, UFO can visualize structural relationships between ontology terms, annotating relationships between entities and terms, and functional similarity between entities. Finally, we demonstrated the ability of UFO through some case studies on finding the best semantic similarity measures for assessing the similarity between human disease phenotypes, constructing biomedical entity functional similarity networks for predicting disease-associated biomarkers, and performing enrichment analysis on a set of similar phenotypes.ConclusionsTaken together, UFO is expected to be a tool where biomedical ontologies can be exploited for various biomedical applications.AvailabilityUFO is distributed as a Cytoscape app, and can be downloaded freely at Cytoscape App (http://apps.cytoscape.org/apps/ufo) for non-commercial use

PyMeSHSim: an integrative python package for biomedical named entity recognition, normalization, and comparison of MeSH terms

BackgroundMany disease causing genes have been identified through different methods, but there have been no uniform annotations of biomedical named entity (bio-NE) of the disease phenotypes of these genes yet. Furthermore, semantic similarity comparison between two bio-NE annotations has become important for data integration or system genetics analysis.ResultsThe package pyMeSHSim recognizes bio-NEs by using MetaMap which produces Unified Medical Language System (UMLS) concepts in natural language process. To map the UMLS concepts to Medical Subject Headings (MeSH), pyMeSHSim is embedded with a house-made dataset containing the main headings (MHs), supplementary concept records (SCRs), and their relations in MeSH. Based on the dataset, pyMeSHSim implemented four information content (IC)-based algorithms and one graph-based algorithm to measure the semantic similarity between two MeSH terms. To evaluate its performance, we used pyMeSHSim to parse OMIM and GWAS phenotypes. The pyMeSHSim introduced SCRs and the curation strategy of non-MeSH-synonymous UMLS concepts, which improved the performance of pyMeSHSim in the recognition of OMIM phenotypes. In the curation of 461 GWAS phenotypes, pyMeSHSim showed recall > 0.94, precision > 0.56, and F1 > 0.70, demonstrating better performance than the state-of-the-art tools DNorm and TaggerOne in recognizing MeSH terms from short biomedical phrases. The semantic similarity in MeSH terms recognized by pyMeSHSim and the previous manual work was calculated by pyMeSHSim and another semantic analysis tool meshes, respectively. The result indicated that the correlation of semantic similarity analysed by two tools reached as high as 0.89–0.99.ConclusionsThe integrative MeSH tool pyMeSHSim embedded with the MeSH MHs and SCRs realized the bio-NE recognition, normalization, and comparison in biomedical text-mining.

Disentangling modal meanings with distributional semantics

AbstractThis article investigates the collocational behavior of English modal auxiliaries such as may and might with the aim of finding corpus-based measures that distinguish between different modal expressions and that allow insights into why speakers may choose one over another in a given context. The analysis uses token-based semantic vector space modeling (Heylen et al., 2015, Monitoring polysemy. Word space models as a tool for large-scale lexical semantic analysis. Lingua, 157: 153–72; Hilpert and Correia Saavedra, 2017, Using token-based semantic vector spaces for corpus-linguistic analyses: From practical applications to tests of theoretical claims. Corpus Linguistics and Linguistic Theory) in order to determine whether different modal auxiliaries can be distinguished in terms of their collocational profiles. The analysis further examines whether different senses of the same auxiliary exhibit divergent collocational preferences. The results indicate that near-synonymous pairs of modal expressions, such as may and might or must and have to, differ in their distributional characteristics. Also, different senses of the same modal expression, such as deontic and epistemic uses of may, can be distinguished on the basis of distributional information. We discuss these results against the background of previous empirical findings (Hilpert, 2016, Construction Grammar and its Application to English, 2nd edn. Edinburgh: Edinburgh University Press, Flach, in press, Beyond modal idioms and modal harmony: a corpus-based analysis of gradient idiomaticity in modal-adverb collocations. English Language and Linguistics) and theoretical issues such as degrees of grammaticalization (Correia Saavedra, 2019, Measurements of Grammaticalization: Developing a Quantitative Index for the Study of Grammatical Change. PhD Dissertation, Université de Neuchâtel) and the avoidance of synonymy (Bolinger, 1968, Entailment and the meaning of structures. Glossa, 2(2): 119–27).

Twitter conversations about food poverty: an analysis supplemented with Google Trends analysis

BackgroundAlthough the UK has not routinely collected national data on household food insecurity, the United Nations estimates that 8·4 million people in the UK experience food insecurity, a point emphasised by UN Special Rapporteur Philip Alston. With the use of novel and mixed methods we explored current topics, communications, and characteristics of social media networks on food poverty posted on Twitter. Our research questions were: what discussions were taking place on Twitter related to food poverty within the specified time? What hashtags, words, and websites were the most mentioned related to food poverty? What word-pair groups emerged by social analysis? MethodsWe used NodeXL Pro software to collect tweets sent between Nov 28 and Nov 30, 2018, using the phrase food poverty. This temporal range controlled for variables associated with food poverty, notably school-aged children and holiday periods, as we used Twitter's free public application programming interface (API) limit of 18 000 tweets and search range of 9 days. We analysed and visualised our data using social and semantic analysis tools such as overall graph metrics, vertex degree, vertex betweenness and closeness centralities, words and word pairs, and Network top items graph metrics. We also explored the spatiotemporal trends associated with this phrase using Google Trends. FindingsWe identified 4843 Twitter users whose recent tweets contained the term food poverty. There was 6039 tweets and connections in our network including 376 unique tweets, 3576 retweets, 1625 mentions, and 462 replies. The users shared information related to the existence of food poverty in the UK. Conversations included the growing numbers of foodbanks, welfare reforms, and Universal Credit as the cause of this problem. Google Trends indicated the highest degree of interest for food poverty search queries was related to New Zealand, followed by the UK and USA. Philip Alston was also the highest search term trend in the UK during this time. InterpretationThis research provides a snapshot of conversations about food poverty on Twitter. The themes we obtained indicate a lack of acknowledgment of food poverty in terms of both social policy and public health in the UK. Capturing and analysing social communications using this approach has highlighted increasing public awareness of food poverty. FundingTeesside University.

Explication of lexicographic information in electronic dictionaries

Background. The level of informativeness and computerization in human activity exacerbates the prob­lem of increasing the ef㌠ciency of automatic processing systems and explicit representation of linguistic in­ formation in them, which is transmitted by means of natural languages. Today, the role of electronic diction­ aries in the information environment is increasing; thus, the interest in the processing of semantic informa­tion by software is enhancing. Purpose. The purpose of the article is to formulate the principles of semantic information in electron­ic interpretative dictionaries, recognized in linguistics as the most reliable and representative source of this information, according to the main requirement, to electronic dictionaries for the presentation of in­ formation in them in an explicit form and structured in such a way that it was possible to carry out its pro­cessing software tools. Methods. The method of component analysis, the theory of semantic states, corpus technologies, and elements of quantitative analysis are applied. Results. The constructed LBD “Semantics of relative adjectives” combines the function of the automatic workplace (ARM) of the researcher and the programmatic and informational tools for conducting semantic studies of adjectives. Discussion. The task of creating a language and information tool for semantic analysis of the semantics of lexical units of the Ukrainian language will be solved using methods of computer linguistics in semantic research on the way of constructing a lexicographic database integrated with the electronic explanatory dic­tionary for a multiparameter description of the semantic properties of words. Article received 30.12.2018

A taxonomy generation tool for semantic visual analysis of large corpus of documents

Taxonomies are semantic resources that help to categorize and add meaning to data. In a hyperconnected world where information is generated at a rate that exceeds human capacities to process and make sense of it, such semantic resources can help to access relevant information more efficiently by extracting knowledge from large and unstructured data sets. Taxonomies are related to specific domains of knowledge in which they identify relevant topics. However, they have to be validated by experts to guarantee that its terms and relations are meaningful. In this paper, we introduce a semiautomatic taxonomy generation tool for supporting domain experts in building taxonomies that are then used to automatically create semantic visualizations of data. Our proposal combines automatic techniques to extract, sort and categorize terms, and empowers domain experts to take part at any stage of the process by providing a visual edition tool. We tested the tool’s usability in two use cases from different domains and languages. Results show that all the functionalities are easy to use and interact with. Lessons learned from this experience will guide the design of a utility evaluation involving domain experts interested in data analysis and knowledge modeling.

From citizens to government policy-makers: Social media data analysis

People are more and more using social media to express themselves about the different services that their governments are delivering. They can either provide positive or negative comments on government services. Hence, it becomes important for policy-makers to have the necessary tools to extract this valuable knowledge in a comprehensive way and that they may consider in their decision-making processes. This paper provides a generic framework, based on semantic analysis of text, to extract valuable data from social media in order to provide new information for government policy-makers. The proposed framework is based on a text semantic analysis tool that collects data from social networks and extracts valuable data to be presented to government policy-makers. The proposed framework is applied to analyze Facebook posts from a page that is managed by citizens in Tunisia. This page aims to report various problems and issues occurring in Tunisian cities.