Mahmoud El-Haj
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Mahmoud El-Haj has a total of 44 co-authors. Here are the top co-authors by number of shared publications:
- Paul Rayson
School of Computing and Communications, Lancaster University, Lancaster, United Kingdom
11 shared publications - Steven Young
Lancaster University Management School, Lancaster University, Lancaster, UK
7 shared publications Martin Walker
5 shared publications- Udo Kruschwitz
University of Regensburg, Regensburg, Germany
4 shared publications - Jo Knight
Lancaster Medical School, Lancaster University, Lancaster, UK
3 shared publications - Scott Piao
Lancaster University
3 shared publications
Latest Publications
- Open Access
- 9 September 2026
- Published by Elsevier in SSRN Electronic Journal
Mandatory Annual Report Disclosure of Business Model and Strategy: Information Asymmetry and Cascade Effects
Policymakers have increasingly encouraged the inclusion of business model and strategy commentary (strategy disclosure) in annual reports as a central pillar of effective corporate reporting. We examine the effects of the UK Corporate Governance Code 2010 that mandated strategy disclosure in annual reports for a subset of London Stock Exchange firms. We begin by investigating whether the mandate induces an increase in annual report strategy disclosure. Our findings confirm a significant increase in strategy disclosure following the mandate, with the effect more consistently identified in presentation-based measures that rely on dedicated strategy sections within annual reports. We then examine the mandate’s effect on aspects of firms’ information environment. First, we examine the effect on investor information asymmetry (proxied by the bid-ask spread) and find a significant reduction following the mandate. Second, we investigate whether strategy disclosure in timelier communication channels (investor presentations and earnings press releases) helps explain this effect. We find evidence that strategy disclosure in complementary channels mediates the relation between annual report strategy disclosure and lower information asymmetry. Overall, our findings suggest that mandated strategy disclosure can improve firms’ information environments both directly through annual report disclosure and indirectly through cascade effects on timelier disclosure channels.
- 9 September 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessMandatory Annual Report Disclosure of Business Model and Strategy: Information Asymmetry and Cascade Effects
Policymakers have increasingly encouraged the inclusion of business model and strategy commentary (strategy disclosure) in annual reports as a central pillar of effective corporate reporting. We examine the effects of the UK Corporate Governance Code 2010 that mandated strategy disclosure in annual reports for a subset of London Stock Exchange firms. We begin by investigating whether the mandate induces an increase in annual report strategy disclosure. Our findings confirm a significant increase in strategy disclosure following the mandate, with the effect more consistently identified in presentation-based measures that rely on dedicated strategy sections within annual reports. We then examine the mandate’s effect on aspects of firms’ information environment. First, we examine the effect on investor information asymmetry (proxied by the bid-ask spread) and find a significant reduction following the mandate. Second, we investigate whether strategy disclosure in timelier communication channels (investor presentations and earnings press releases) helps explain this effect. We find evidence that strategy disclosure in complementary channels mediates the relation between annual report strategy disclosure and lower information asymmetry. Overall, our findings suggest that mandated strategy disclosure can improve firms’ information environments both directly through annual report disclosure and indirectly through cascade effects on timelier disclosure channels.
- Open Access
- 17 November 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Asian and Low-Resource Language Information Processing
- Vol. 24 (11) , 1-21
Complex Concept-Based Readability Estimation from Arabic Curriculum
This article presents an approach to readability estimation that focuses on conceptual rather than linguistic complexity, using the extensive SaudiTextBooks textbooks. We introduce DARES 2.0 , an enhanced concept-based readability training dataset designed to estimate the readability of Saudi educational texts. Building on DARES 1.0, DARES 2.0 extends the scope of conceptual complexity by replacing repetitive concepts and manually revising the input features with unique terms and their surrounding contexts from the SaudiTextBooks, spanning grades 1 to 12. The refined DARES 2.0 is employed to fine-tune pre-trained transformer models, including XLM-R Base, mBERT, AraELECTRA, AraBERTv2, and CAMeLBERTmix. The findings suggest that both the dataset and experimental setup require further development to ensure a larger, higher-quality dataset and to support more extensive fine-tuning experiments, in addition to exploring transfer learning from other languages and enhancing the diversity and richness of Arabic concepts. These developments pave the way for further advancements in concept-based readability estimation in educational contexts in future work.
- 17 November 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Asian and Low-Resource Language Information Processing
- Vol. 24 (11) , 1-21
Open AccessComplex Concept-Based Readability Estimation from Arabic Curriculum
This article presents an approach to readability estimation that focuses on conceptual rather than linguistic complexity, using the extensive SaudiTextBooks textbooks. We introduce DARES 2.0 , an enhanced concept-based readability training dataset designed to estimate the readability of Saudi educational texts. Building on DARES 1.0, DARES 2.0 extends the scope of conceptual complexity by replacing repetitive concepts and manually revising the input features with unique terms and their surrounding contexts from the SaudiTextBooks, spanning grades 1 to 12. The refined DARES 2.0 is employed to fine-tune pre-trained transformer models, including XLM-R Base, mBERT, AraELECTRA, AraBERTv2, and CAMeLBERTmix. The findings suggest that both the dataset and experimental setup require further development to ensure a larger, higher-quality dataset and to support more extensive fine-tuning experiments, in addition to exploring transfer learning from other languages and enhancing the diversity and richness of Arabic concepts. These developments pave the way for further advancements in concept-based readability estimation in educational contexts in future work.
- 14 June 2023
- Published by Springer Nature
- p. 391-403
A Comparative Study of Evaluation Metrics for Long-Document Financial Narrative Summarization with Transformers
- 14 June 2023
- Published by Springer Nature
- p. 391-403
A Comparative Study of Evaluation Metrics for Long-Document Financial Narrative Summarization with Transformers
- Open Access
A Data-driven Latent Semantic Analysis for Automatic Text Summarization using LDA Topic Modelling
With the advent and popularity of big data mining and huge text analysis in modern times, automated text summarization became prominent for extracting and retrieving important information from documents. This research investigates aspects of automatic text summarization from the perspectives of single and multiple documents. Summarization is a task of condensing huge text articles into short, summarized versions. The text is reduced in size for summarization purpose but preserving key vital information and retaining the meaning of the original document. This study presents the Latent Dirichlet Allocation (LDA) approach used to perform topic modelling from summarised medical science journal articles with topics related to genes and diseases. In this study, PyLDAvis web-based interactive visualization tool was used to visualise the selected topics. The visualisation provides an overarching view of the main topics while allowing and attributing deep meaning to the prevalence individual topic. This study presents a novel approach to summarization of single and multiple documents. The results suggest the terms ranked purely by considering their probability of the topic prevalence within the processed document using extractive summarization technique. PyLDAvis visualization describes the flexibility of exploring the terms of the topics' association to the fitted LDA model. The topic modelling result shows prevalence within topics 1 and 2. This association reveals that there is similarity between the terms in topic 1 and 2 in this study. The efficacy of the LDA and the extractive summarization methods were measured using Latent Semantic Analysis (LSA) and Recall-Oriented Understudy for Gisting Evaluation (ROUGE) metrics to evaluate the reliability and validity of the model.
Open AccessA Data-driven Latent Semantic Analysis for Automatic Text Summarization using LDA Topic Modelling
With the advent and popularity of big data mining and huge text analysis in modern times, automated text summarization became prominent for extracting and retrieving important information from documents. This research investigates aspects of automatic text summarization from the perspectives of single and multiple documents. Summarization is a task of condensing huge text articles into short, summarized versions. The text is reduced in size for summarization purpose but preserving key vital information and retaining the meaning of the original document. This study presents the Latent Dirichlet Allocation (LDA) approach used to perform topic modelling from summarised medical science journal articles with topics related to genes and diseases. In this study, PyLDAvis web-based interactive visualization tool was used to visualise the selected topics. The visualisation provides an overarching view of the main topics while allowing and attributing deep meaning to the prevalence individual topic. This study presents a novel approach to summarization of single and multiple documents. The results suggest the terms ranked purely by considering their probability of the topic prevalence within the processed document using extractive summarization technique. PyLDAvis visualization describes the flexibility of exploring the terms of the topics' association to the fitted LDA model. The topic modelling result shows prevalence within topics 1 and 2. This association reveals that there is similarity between the terms in topic 1 and 2 in this study. The efficacy of the LDA and the extractive summarization methods were measured using Latent Semantic Analysis (LSA) and Recall-Oriented Understudy for Gisting Evaluation (ROUGE) metrics to evaluate the reliability and validity of the model.
- 23 November 2022
- Published by Taylor & Francis
- p. 96-120
Semantic domains across topics, genders and languages
In this chapter, we analyse the semantic domains of words used in texts written by bilingual university-level students in Arabic and English, using a semantic tagger for each language to annotate each word in a text with a semantic domain or sub-domain (e.g. “B2: Health and Disease” or “A6.1 Comparing: similar/different”). First, we review the USAS semantic tagging system, as used in previous research on English and other languages. We then describe the development of the first open source Arabic semantic tagger (AraSAS) and evaluate the tagger’s lexical coverage in relation to that of the English version. Finally, we apply the USAS and AraSAS semantic taggers to the Zayed Arabic-English Bilingual Undergraduate Corpus (ZAEBUC) (Habash and Palfreyman, 2022), in order to compare on a semantic level: (a) texts on different topics, (b) texts written by the same writer in Arabic and in English; and (c) texts written by male and by female students. Variables for comparison include frequency of use of particular semantic sub-domains, as well as the diversity of semantic elements within a text. We draw some tentative conclusions about how topic, gender and bilingualism may interact in written production.
- 23 November 2022
- Published by Taylor & Francis
- p. 96-120
Semantic domains across topics, genders and languages
In this chapter, we analyse the semantic domains of words used in texts written by bilingual university-level students in Arabic and English, using a semantic tagger for each language to annotate each word in a text with a semantic domain or sub-domain (e.g. “B2: Health and Disease” or “A6.1 Comparing: similar/different”). First, we review the USAS semantic tagging system, as used in previous research on English and other languages. We then describe the development of the first open source Arabic semantic tagger (AraSAS) and evaluate the tagger’s lexical coverage in relation to that of the English version. Finally, we apply the USAS and AraSAS semantic taggers to the Zayed Arabic-English Bilingual Undergraduate Corpus (ZAEBUC) (Habash and Palfreyman, 2022), in order to compare on a semantic level: (a) texts on different topics, (b) texts written by the same writer in Arabic and in English; and (c) texts written by male and by female students. Variables for comparison include frequency of use of particular semantic sub-domains, as well as the diversity of semantic elements within a text. We draw some tentative conclusions about how topic, gender and bilingualism may interact in written production.
- Open Access
- 9 April 2022
- Published by MDPI AG in Applied Sciences
- Vol. 12 (8) , 3806
MULDASA: Multifactor Lexical Sentiment Analysis of Social-Media Content in Nonstandard Arabic Social Media
The semantically complicated Arabic natural vocabulary, and the shortage of available techniques and skills to capture Arabic emotions from text hinder Arabic sentiment analysis (ASA). Evaluating Arabic idioms that do not follow a conventional linguistic framework, such as contemporary standard Arabic (MSA), complicates an incredibly difficult procedure. Here, we define a novel lexical sentiment analysis approach for studying Arabic language tweets (TTs) from specialized digital media platforms. Many elements comprising emoji, intensifiers, negations, and other nonstandard expressions such as supplications, proverbs, and interjections are incorporated into the MULDASA algorithm to enhance the precision of opinion classifications. Root words in multidialectal sentiment LX are associated with emotions found in the content under study via a simple stemming procedure. Furthermore, a feature–sentiment correlation procedure is incorporated into the proposed technique to exclude viewpoints expressed that seem to be irrelevant to the area of concern. As part of our research into Saudi Arabian employability, we compiled a large sample of TTs in 6 different Arabic dialects. This research shows that this sentiment categorization method is useful, and that using all of the characteristics listed earlier improves the ability to accurately classify people’s feelings. The classification accuracy of the proposed algorithm improved from 83.84% to 89.80%. Our approach also outperformed two existing research projects that employed a lexical approach for the sentiment analysis of Saudi dialects.
- 9 April 2022
- Published by MDPI AG in Applied Sciences
- Vol. 12 (8) , 3806
Open AccessMULDASA: Multifactor Lexical Sentiment Analysis of Social-Media Content in Nonstandard Arabic Social Media
The semantically complicated Arabic natural vocabulary, and the shortage of available techniques and skills to capture Arabic emotions from text hinder Arabic sentiment analysis (ASA). Evaluating Arabic idioms that do not follow a conventional linguistic framework, such as contemporary standard Arabic (MSA), complicates an incredibly difficult procedure. Here, we define a novel lexical sentiment analysis approach for studying Arabic language tweets (TTs) from specialized digital media platforms. Many elements comprising emoji, intensifiers, negations, and other nonstandard expressions such as supplications, proverbs, and interjections are incorporated into the MULDASA algorithm to enhance the precision of opinion classifications. Root words in multidialectal sentiment LX are associated with emotions found in the content under study via a simple stemming procedure. Furthermore, a feature–sentiment correlation procedure is incorporated into the proposed technique to exclude viewpoints expressed that seem to be irrelevant to the area of concern. As part of our research into Saudi Arabian employability, we compiled a large sample of TTs in 6 different Arabic dialects. This research shows that this sentiment categorization method is useful, and that using all of the characteristics listed earlier improves the ability to accurately classify people’s feelings. The classification accuracy of the proposed algorithm improved from 83.84% to 89.80%. Our approach also outperformed two existing research projects that employed a lexical approach for the sentiment analysis of Saudi dialects.
- 4 December 2021
- Published by Oxford University Press (OUP) in International Journal of Lexicography
- Vol. 35 (3) , 364-377
A Domain Based Approach to Semantic Lexicon Expansion
Current approaches to the expansion of semantic lexicons for corpus annotation are somewhat ad hoc in nature and do not generally offer a systematic means of identifying areas for development within one’s lexicon. The present paper sets forward a domain based approach to semantic lexicon expansion, targeting UCREL’s Semantic Analysis System (USAS). First, an updated version of the lexicon is compared to representative corpora to ascertain areas of underrepresentation in a novel method which we call K-FLUX analysis. Second, an example set of underrepresented types are targeted for development using domain specific corpora. Collectively, the results show that some corpora are more successful than others in supplementing the existing USAS lexicon. The paper discusses the various factors that should be borne in mind when utilising the proposed method before concluding with how findings might inform future developments of the lexicon, and crucially, the semantic system on which it is based.
- 4 December 2021
- Published by Oxford University Press (OUP) in International Journal of Lexicography
- Vol. 35 (3) , 364-377
A Domain Based Approach to Semantic Lexicon Expansion
Current approaches to the expansion of semantic lexicons for corpus annotation are somewhat ad hoc in nature and do not generally offer a systematic means of identifying areas for development within one’s lexicon. The present paper sets forward a domain based approach to semantic lexicon expansion, targeting UCREL’s Semantic Analysis System (USAS). First, an updated version of the lexicon is compared to representative corpora to ascertain areas of underrepresentation in a novel method which we call K-FLUX analysis. Second, an example set of underrepresented types are targeted for development using domain specific corpora. Collectively, the results show that some corpora are more successful than others in supplementing the existing USAS lexicon. The paper discusses the various factors that should be borne in mind when utilising the proposed method before concluding with how findings might inform future developments of the lexicon, and crucially, the semantic system on which it is based.
- 23 July 2021
- Published by John Benjamins Publishing Company in Corpus Studies of Language Through Time
- Vol. 26 (3) , 305-335
Problematising characteristicness
Keyness is a commonly used method in corpus linguistics and is assumed to identify key items that are characteristic of 1 corpus when compared to another. This paper puts this assumption to the test by comparing case study corpora in the fields of genetic, immunological and psychiatric biomedical association studies, using what we refer to as a ‘K-FLUX’ analysis to produce a set of key items. Experts from within these fields are asked to evaluate the extent to which identified key items are characteristic of their discipline. The paper concludes that less than 50% of the items identified by the method are rated as highly characteristic by experts and that this ranges between types of association study. Further, there is difficulty in reaching a consensus over what is deemed to be ‘characteristic’, thus posing a challenge to the ultimate aim of the keyness method. The paper demonstrates the value of supporting corpus linguistic studies with expert assessments to evaluate whether (and which) items can be said to be indicative of a particular field.
- 23 July 2021
- Published by John Benjamins Publishing Company in Corpus Studies of Language Through Time
- Vol. 26 (3) , 305-335
Problematising characteristicness
Keyness is a commonly used method in corpus linguistics and is assumed to identify key items that are characteristic of 1 corpus when compared to another. This paper puts this assumption to the test by comparing case study corpora in the fields of genetic, immunological and psychiatric biomedical association studies, using what we refer to as a ‘K-FLUX’ analysis to produce a set of key items. Experts from within these fields are asked to evaluate the extent to which identified key items are characteristic of their discipline. The paper concludes that less than 50% of the items identified by the method are rated as highly characteristic by experts and that this ranges between types of association study. Further, there is difficulty in reaching a consensus over what is deemed to be ‘characteristic’, thus posing a challenge to the ultimate aim of the keyness method. The paper demonstrates the value of supporting corpus linguistic studies with expert assessments to evaluate whether (and which) items can be said to be indicative of a particular field.
- Top Cited PapersOpen Access
- 25 July 2019
- Published by Taylor & Francis in Accounting and Business Research
- Vol. 50 (1) , 6-34
Retrieving, classifying and analysing narrative commentary in unstructured (glossy) annual reports published as PDF files
We provide a methodological contribution by developing, describing and evaluating a method for automatically retrieving and analysing text from digital PDF annual report files published by firms listed on the London Stock Exchange (LSE). The retrieval method retains information on document structure, enabling clear delineation between narrative and financial statement components of reports, and between individual sections within the narratives component. Retrieval accuracy exceeds 95% for manual validations using a random sample of 586 reports. Large-sample statistical validations using a comprehensive sample of reports published by non-financial LSE firms confirm that report length, narrative tone and (to a lesser degree) readability vary predictably with economic and regulatory factors. We demonstrate how the method is adaptable to non-English language documents and different regulatory regimes using a case study of Portuguese reports. We use the procedure to construct new research resources including corpora for commonly occurring annual report sections and a dataset of text properties for over 26,000 U.K. annual reports.
- 25 July 2019
- Published by Taylor & Francis in Accounting and Business Research
- Vol. 50 (1) , 6-34
Top Cited PapersOpen AccessRetrieving, classifying and analysing narrative commentary in unstructured (glossy) annual reports published as PDF files
We provide a methodological contribution by developing, describing and evaluating a method for automatically retrieving and analysing text from digital PDF annual report files published by firms listed on the London Stock Exchange (LSE). The retrieval method retains information on document structure, enabling clear delineation between narrative and financial statement components of reports, and between individual sections within the narratives component. Retrieval accuracy exceeds 95% for manual validations using a random sample of 586 reports. Large-sample statistical validations using a comprehensive sample of reports published by non-financial LSE firms confirm that report length, narrative tone and (to a lesser degree) readability vary predictably with economic and regulatory factors. We demonstrate how the method is adaptable to non-English language documents and different regulatory regimes using a case study of Portuguese reports. We use the procedure to construct new research resources including corpora for commonly occurring annual report sections and a dataset of text properties for over 26,000 U.K. annual reports.
- Open Access
- 1 July 2019
- Published by SLACK, Inc. in HLRP: Health Literacy Research and Practice
- Vol. 3 (3) , e170-e173
Readability of Patient Educational Materials in English Versus Arabic
Little research has been done about patient educational materials (PEMs) written in Arabic. Readability of Arabic PEMs has not previously been assessed because, until recently, there was no validated Arabic readability assessment tool. A total of 207 PEMs in both Arabic and English were collected from the Medline Plus portal. Readability was assessed using Flesch-Kincaid in English and the Open Source Metric for Measuring Arabic Narratives, a new Arabic readability test. We also examined Arabic documents for other linguistic features that could lead to confusion. Mean readability grades were 6.1 and 7.1 for Arabic and English, respectively (p < .01). In 31.6% of PEMs, the English text was higher by two or more grades than the Arabic text, and the Arabic text was higher by two or more grades than the English text in 3.8% of PEMs. No diacritical marks in Arabic were used. An array of esoteric Arabic medical terms, transliterated English terms, Arabicized English terms, and written versions of spoken Arabic dialects were used. [ HLRP: Health Literacy Research and Practice . 2019;3(3):e170–e173.]
- 1 July 2019
- Published by SLACK, Inc. in HLRP: Health Literacy Research and Practice
- Vol. 3 (3) , e170-e173
Open AccessReadability of Patient Educational Materials in English Versus Arabic
Little research has been done about patient educational materials (PEMs) written in Arabic. Readability of Arabic PEMs has not previously been assessed because, until recently, there was no validated Arabic readability assessment tool. A total of 207 PEMs in both Arabic and English were collected from the Medline Plus portal. Readability was assessed using Flesch-Kincaid in English and the Open Source Metric for Measuring Arabic Narratives, a new Arabic readability test. We also examined Arabic documents for other linguistic features that could lead to confusion. Mean readability grades were 6.1 and 7.1 for Arabic and English, respectively (p < .01). In 31.6% of PEMs, the English text was higher by two or more grades than the Arabic text, and the Arabic text was higher by two or more grades than the English text in 3.8% of PEMs. No diacritical marks in Arabic were used. An array of esoteric Arabic medical terms, transliterated English terms, Arabicized English terms, and written versions of spoken Arabic dialects were used. [ HLRP: Health Literacy Research and Practice . 2019;3(3):e170–e173.]