Dr. Najmeh Mousavi Nejad – Smart Data Analytics

PhD Student
Computer Science Institute
University of Bonn

Profiles: LinkedIn, Google Scholar, DBLP

najmehsadat.mousavinezhad@iais.fraunhofer.de

Short CV

Dr. Najmeh Mousavi Nejad is a PhD Student at the University of Bonn. She received her master’s degree in Artificial Intelligence in 2011 in Iran, following which she accumulated research experience supported by publications as well as working experience in industry. Since 2015, she is the recipient of a DAAD scholarship (German Academic Exchange Service) for PhD studies in Germany and continues to conduct research (also received a nomination for Best Research and Innovation Paper award in an international conference). Her research interests are semantic web, text mining and analysis, information extraction & retrieval and Natural language processing.

Research Interests

Semantic Web
Text mining and analysis
Information Extraction
Natural Language Processing

Projects

PLATOON
QualiChain
DAPSI

Publications

2021

Mousavinezhad, Najmeh

Knowledge Extraction Methods for the Analysis of Contractual Agreements PhD Thesis

Rheinische Friedrich-Wilhelms-Universität Bonn, 2021.

Abstract | BibTeX

@phdthesis{,

title = {Knowledge Extraction Methods for the Analysis of Contractual Agreements},

author = {Najmeh Mousavinezhad},

year  = {2021},

date = {2021-05-31},

school = {Rheinische Friedrich-Wilhelms-Universität Bonn},

abstract = {The ubiquitous availability of the Internet results in a massive number of apps, software, and online services with accompanying contractual agreements in the form of end-user license agreement' andprivacy policy’. Often the textual documents describing rights, policies, and conditions comprise many pages and can not be reasonably assumed to be read and understood by humans. Although everyone is exposed to such consent forms, the majority tend to ignore them due to their length and complexity. However, the cost of ignoring terms and conditions is not always negligible, and occasionally people have to pay (money or other means) as a result of their oversight. In this thesis, we focus on the interpretation of contractual agreements for the benefit of end-users. Contractual agreements encompass both the privacy policies and the general terms and conditions related to software and services. The main characteristics of such agreements are their use of legal terminologies and limited vocabulary. This feature has pros and cons. On one hand, the clear structure and legal language facilitate the mapping between the human-readable agreements and machine-processable concepts. On the other hand, the legal terminologies make the contractual agreement complex, subjective, and, therefore, open to interpretation. This thesis addresses the problem of contractual agreement analysis from both perspectives. In order to provide a structured presentation of contractual agreements, we apply text mining and semantic technologies to develop approaches that extract important information from the agreements and retrieve helpful links and resources for better comprehension. Our approaches are based on ontology-based information extraction, machine learning, and semantic similarity and aim to deliver tedious consent forms in a user friendly and visualized format. The ontology-based information extraction approach processes the human-readable license agreement guided by a domain ontology to extract deontic modalities and presents a summarized output to the end-user. In the extraction phase, we focus on three key rights and conditions: permission, prohibition, duty and cluster the extracted excerpts according to their similarities. The clustering is based on semantic similarity employing a distributional semantics approach on large word embeddings database. The machine learning method employs deep neural networks to classify a privacy policy’s paragraphs into pre-defined categories. Since the prediction results of the trained model are promising, we further use the predicted classes to assign five risk colors (Green, Yellow, Red) to five privacy icons (Expected Use, Expected Collection, Precise Location, Data Retention and Children Privacy). Furthermore, given that any contractual agreement must comply with the relevant legislation, we utilize text semantic similarity to map an agreement’s content to regulatory documents. The semantic similarity-based approach finds candidate sentences in an agreement that are potentially related to specific articles in the regulation. Then, for each candidate sentence, the relevant article and provision is found according to their semantic similarity. The achieved results from our proposed approaches allow us to conclude that although semi-automatic approaches lead to information loss, they save time and effort by producing instant results and facilitate the end-users understanding of legal texts.},

keywords = {},

pubstate = {published},

tppubtype = {phdthesis}

}

The ubiquitous availability of the Internet results in a massive number of apps, software, and online services with accompanying contractual agreements in the form of end-user license agreement' andprivacy policy’. Often the textual documents describing rights, policies, and conditions comprise many pages and can not be reasonably assumed to be read and understood by humans. Although everyone is exposed to such consent forms, the majority tend to ignore them due to their length and complexity. However, the cost of ignoring terms and conditions is not always negligible, and occasionally people have to pay (money or other means) as a result of their oversight. In this thesis, we focus on the interpretation of contractual agreements for the benefit of end-users. Contractual agreements encompass both the privacy policies and the general terms and conditions related to software and services. The main characteristics of such agreements are their use of legal terminologies and limited vocabulary. This feature has pros and cons. On one hand, the clear structure and legal language facilitate the mapping between the human-readable agreements and machine-processable concepts. On the other hand, the legal terminologies make the contractual agreement complex, subjective, and, therefore, open to interpretation. This thesis addresses the problem of contractual agreement analysis from both perspectives. In order to provide a structured presentation of contractual agreements, we apply text mining and semantic technologies to develop approaches that extract important information from the agreements and retrieve helpful links and resources for better comprehension. Our approaches are based on ontology-based information extraction, machine learning, and semantic similarity and aim to deliver tedious consent forms in a user friendly and visualized format. The ontology-based information extraction approach processes the human-readable license agreement guided by a domain ontology to extract deontic modalities and presents a summarized output to the end-user. In the extraction phase, we focus on three key rights and conditions: permission, prohibition, duty and cluster the extracted excerpts according to their similarities. The clustering is based on semantic similarity employing a distributional semantics approach on large word embeddings database. The machine learning method employs deep neural networks to classify a privacy policy’s paragraphs into pre-defined categories. Since the prediction results of the trained model are promising, we further use the predicted classes to assign five risk colors (Green, Yellow, Red) to five privacy icons (Expected Use, Expected Collection, Precise Location, Data Retention and Children Privacy). Furthermore, given that any contractual agreement must comply with the relevant legislation, we utilize text semantic similarity to map an agreement’s content to regulatory documents. The semantic similarity-based approach finds candidate sentences in an agreement that are potentially related to specific articles in the regulation. Then, for each candidate sentence, the relevant article and provision is found according to their semantic similarity. The achieved results from our proposed approaches allow us to conclude that although semi-automatic approaches lead to information loss, they save time and effort by producing instant results and facilitate the end-users understanding of legal texts.

2020

Nejad, Najmeh Mousavi; Jabat, Pablo; Nedelchev, Rostislav; Scerri, Simon; Graux, Damien

Establishing a Strong Baseline for Privacy Policy Classification Inproceedings

In: ICT Systems Security and Privacy Protection - 35th IFIP TC 11 International Conference, SEC 2020, Maribor, Slovenia, September 21-23, 2020, Proceedings, pp. 370–383, Springer, 2020.

Links | BibTeX

2019

Nejad, Najmeh Mousavi; Graux, Damien; Collarana, Diego

Towards Measuring Risk Factors in Privacy Policies Inproceedings

In: Proceedings of the Workshop on Artificial Intelligence and the Administrative State co-located with 17th International Conference on AI and Law (ICAIL 2019), Montreal, QC, Canada, June 17, 2019, pp. 18–20, CEUR-WS.org, 2019.

Links | BibTeX

2018

Nejad, Najmeh Mousavi

Semantic Analysis of Contractual Agreements to Support End-User Interpretation Inproceedings

In: Proceedings of the EKAW Doctoral Consortium 2018 co-located with the 21st International Conference on Knowledge Engineering and Knowledge Management (EKAW 2018), Nancy, France, November 13, 2018, CEUR-WS.org, 2018.

Links | BibTeX

Nejad, Najmeh Mousavi; Scerri, Simon; Lehmann, Jens

KnIGHT: Mapping Privacy Policies to GDPR Inproceedings

In: Knowledge Engineering and Knowledge Management - 21st International Conference, EKAW 2018, Nancy, France, November 12-16, 2018, Proceedings, pp. 258–272, Springer, 2018.

Links | BibTeX

2017

Nejad, Najmeh Mousavi; Scerri, Simon; Auer, Sören

In: Proceedings of the 13th International Conference on Semantic Systems, SEMANTICS 2017, Amsterdam, The Netherlands, September 11-14, 2017, pp. 144–151, ACM, 2017.

Links | BibTeX

2016

Nejad, Najmeh Mousavi; Scerri, Simon; Auer, Sören; Sibarani, Elisa Margareth

EULAide: Interpretation of End-User License Agreements using Ontology-Based Information Extraction Inproceedings

In: Proceedings of the 12th International Conference on Semantic Systems, SEMANTICS 2016, Leipzig, Germany, September 12-15, 2016, pp. 73–80, ACM, 2016.

Links | BibTeX

2011

Nejad, Najmeh Mousavi; Khadivi, Shahram

An Unsupervised Alignment Model for Sequence Labeling: Application to Name Transliteration Inproceedings

In: Proceedings of the 3rd Named Entities Workshop, NEWS@IJCNLP 2011, Chiang Mai, Thailand, November 12, 2011, pp. 73–81, Asian Federation of Natural Language Processing, 2011.

Links | BibTeX

Nejad, Najmeh Mousavi; Khadivi, Shahram; Taghipour, Kaveh

The Amirkabir Machine Transliteration System for NEWS 2011: Farsi-to-English Task Inproceedings

In: Proceedings of the 3rd Named Entities Workshop, NEWS@IJCNLP 2011, Chiang Mai, Thailand, November 12, 2011, pp. 91–95, Asian Federation of Natural Language Processing, 2011.

Links | BibTeX