Raji Ghawi | Technical University of Munich (original) (raw)

Papers by Raji Ghawi

arXiv (Cornell University), Mar 12, 2024

Technology-facilitated gender-based violence has become a global threat to women's political repr... more Technology-facilitated gender-based violence has become a global threat to women's political representation and democracy. Understanding how online hate affects its targets is thus paramount. We analyse 10 million tweets directed at female candidates in the Brazilian election in 2022 and examine their reactions to online misogyny. Using a self-trained machine learning classifier to detect Portuguese misogynistic tweets and a quantitative analysis of the candidates' tweeting behaviour, we investigate how the number of misogynistic attacks received alters the online activity of the female candidates. We find that young and left-wing candidates and candidates with higher visibility online received significantly more attacks. Furthermore, we find that an increase in misogynistic attacks in the previous week is associated with a decrease in female candidates' tweets in the following week. This potentially threatens their equal participation in public opinion building and silences women's voices in political discourse.

Lecture Notes in Computer Science, 2022

Social Network Analysis and Mining, Jul 10, 2021

The history of intellectuals consists of a complex web of influences and interconnections of phil... more The history of intellectuals consists of a complex web of influences and interconnections of philosophers, scientists, writers, their work, and ideas. To understand how did these influences evolve over time, we mined a network of influence of over 12,500 intellectuals, enriched it with a temporal dimension dividing the history into six eras. We analyze time-sliced projections of the network into within-era, inter-era, and accumulated-era networks, and identify various patterns of intellectuals and eras and studied their development in time. We also construct influence cascades, analyze their properties: size, depth and breadth, and analyze how the cascades of influence evolve over the consecutive eras. We find out that the cascades are clustered into two categories, namely small-and large cascades. An interesting finding here is that the fraction of small cascades increases, while the fraction of larges cascades decreases over time. We also briefly analyze the community structure within the influence network of scholars.

The history of intellectuals consists of a complicated web of influences and interconnections of ... more The history of intellectuals consists of a complicated web of influences and interconnections of philosophers, scientists, writers, their work, and ideas. How did these influences evolve over time? Who were the most influential scholars in a period? To answer these questions, we mined a network of influence of over 12,500 intellectuals, extracted from the Linked Open Data provider YAGO. We enriched this network with a longitudinal perspective, and analysed time-sliced projections of the complete network differentiating between within-era, inter-era, and accumulated-era networks. We thus identified various patterns of intellectuals and eras, and studied their development in time. We show which scholars were most influential in different eras, and who took prominent knowledge broker roles. One essential finding is that the highest impact of an era's scholar was on their contemporaries, as well as the inter-era influence of each period was strongest to its consecutive one. Further, we see quantitative evidence that there was no re-discovery of Antiquity during the Renaissance, but a continuous reception since the Middle Ages.

Social Network Analysis and Mining, Jun 7, 2022

Negative word-of-mouth is a strong consumer and user response to dissatisfaction. Moral outrages ... more Negative word-of-mouth is a strong consumer and user response to dissatisfaction. Moral outrages can create an excessive collective aggressiveness against one single argument, one single word, or one action of a person resulting in hateful speech. In this work, we examine the change of vocabulary to explore the outbreak of online firestorms on Twitter. The sudden change of an emotional state can be captured in language. It reveals how people connect with each other to form outrage. We find that when users turn their outrage against somebody, the occurrence of self-referencing pronouns like 'I' and 'me' reduces significantly. Using data from Twitter, we derive such linguistic features together with features based on retweets and mention networks to use them as indicators for negative word-of-mouth dynamics in social media networks. Based on these features, we build three classification models that can predict the outbreak of a firestorm with high accuracy.

Intellectuals, scholars, philosophers, writers, and scientists, and their work are embedded in a ... more Intellectuals, scholars, philosophers, writers, and scientists, and their work are embedded in a long history of ideas. These traditions disseminated and diffused over a long history spanning from Greek-Roman antiquity to recent times. But how did those lines of traditions and influence of thoughts develop over the ages? How did intellectuals influence each other? What is the most far-reaching impact of influence, as well as who are the most immediate influencing, and the most influenced by other intellectuals in history? To answer these types of questions, we mined a network of influence among over 12 thousand intellectuals, from YAGO, a pioneering data source of Linked Open Data. We conducted several essential types of social network analysis, concerning connectivity, degree distribution, prestige (influence), and importance (centrality). We studied the diffusion dynamics of influence by analyzing the influence cascades in terms of size, depth and breadth. One interesting finding is the identification of two major, disjoint categories of small and large cascades of influence.

Virtual teams are becoming increasingly important. Since they are digital in nature, their "trace... more Virtual teams are becoming increasingly important. Since they are digital in nature, their "trace data" enable a broad set of new research opportunities. Online Games are especially useful for studying social behavior patterns of collaborative teams. In our study we used longitudinal data from the Massively Multiplayer Online Game (MMOG) Travian collected over a 12month period that included 4,753 teams with 18,056 individuals and their communication networks. For predicting team performance, we selected 13 SNA-based attributes frequently used in team and leadership research. Using machine learning algorithms, the added explanatory power derived from the patterns of the communication networks enabled us to achieve an adjusted R 2 = 0.67 in the best fitting performance prediction model and a prediction accuracy of up to 95.3% in the classification of top performing teams.

Social Networks, 2022

Abstract In multilayer networks, quantifying layer similarity is of great importance for many app... more Abstract In multilayer networks, quantifying layer similarity is of great importance for many applications. Traditional approaches to measure layer similarities rely mainly on micro-level features of network structures, such as node degree. In this paper, we propose to use mesoscopic network structures, i.e., communities, to assess layer similarity. Our proposed approach is based on matching the communities detected at the layers being compared. The similarity is thus defined using clustering evaluation methods such as purity and F-measure. Our results on empirical datasets show that the proposed approach provides more consistent layer taxonomies than other approaches.

2022 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM)

Lecture Notes in Computer Science, 2022

2018 14th International Conference on Signal-Image Technology & Internet-Based Systems (SITIS)

We propose a semantic-based methodology for Social Network Analysis (SNA). This methodology addre... more We propose a semantic-based methodology for Social Network Analysis (SNA). This methodology addresses computations needed for SNA in a declarative way -in contrast to traditional SNA where computations are procedural. Our ingredients are semantic technologies: We define an ontology to represent graphs, their components (nodes, edges or paths), and the structural relationships between these components. We exploit reasoning capabilities of ontologies to infer structural relations between graph components. We also use ontological queries to perform computations needed in SNA. To demonstrate how does this approach work, we present three showcases of typical network analysis: basic metrics, triadic census, and betweenness centrality. The proposed approaches offer several computational opportunities for analyzing networks with respect to calculation of path-dependent centrality metrics, e.g. in distributed setups.

Social Network Analysis and Mining

Negative word-of-mouth is a strong consumer and user response to dissatisfaction. Moral outrages ... more Negative word-of-mouth is a strong consumer and user response to dissatisfaction. Moral outrages can create an excessive collective aggressiveness against one single argument, one single word, or one action of a person resulting in hateful speech. In this work, we examine the change of vocabulary to explore the outbreak of online firestorms on Twitter. The sudden change of an emotional state can be captured in language. It reveals how people connect with each other to form outrage. We find that when users turn their outrage against somebody, the occurrence of self-referencing pronouns like ‘I’ and ‘me’ reduces significantly. Using data from Twitter, we derive such linguistic features together with features based on retweets and mention networks to use them as indicators for negative word-of-mouth dynamics in social media networks. Based on these features, we build three classification models that can predict the outbreak of a firestorm with high accuracy.

Online firestorms on Twitter are seemingly arbitrarily occurring outrages towards people, compani... more Online firestorms on Twitter are seemingly arbitrarily occurring outrages towards people, companies, media campaigns and politicians. Moral outrages can create an excessive collective aggressiveness against one single argument, one single word, or one action of a person resulting in hateful speech. With a collective "against the others" the negative dynamics often start. Using data from Twitter, we explored the starting points of several firestorm outbreaks. As a social media platform with hundreds of millions of users interacting in real-time on topics and events all over the world, Twitter serves as a social sensor for online discussions and is known for quick and often emotional disputes. The main question we pose in this article, is whether we can detect the outbreak of a firestorm. Given 21 online firestorms on Twitter, the key questions regarding the anomaly detection are: 1) How can we detect the changing point? 2) How can we distinguish the features that cause a mo...

The history of intellectuals consists of a complicated web of influences and interconnections of ... more The history of intellectuals consists of a complicated web of influences and interconnections of philosophers, scientists, writers, their work, and ideas. How did these influences evolve over time? Who were the most influential scholars in a period? To answer these questions, we mined a network of influence of over 12,500 intellectuals, extracted from the Linked Open Data provider YAGO. We enriched this network with a longitudinal perspective, and analysed time-sliced projections of the complete network differentiating between within-era, inter-era, and accumulated-era networks. We thus identified various patterns of intellectuals and eras, and studied their development in time. We show which scholars were most influential in different eras, and who took prominent knowledge broker roles. One essential finding is that the highest impact of an era's scholar was on their contemporaries, as well as the inter-era influence of each period was strongest to its consecutive one. Further,...

The growing amount of distributed data over the internet leads to increasing needs for interopera... more The growing amount of distributed data over the internet leads to increasing needs for interoperability. Being able to take into account the meaning of information is a real challenge for suitable data sharing. The semantic web and the ontologies are relevant technologies to provide semantic cooperation of heterogeneous sources. We propose a complete architecture OWSCIS (Ontology and Web Service based Cooperation of Information Sources) which allows to query a cooperation of information sources. The semantic of the local data is expressed using local ontologies which are mapped to a reference ontology. This reference ontology can be queried by an end user to transparently access the cooperation. The different components of the architecture are described: the data providers, the knowledge base, the interontology mapping process, the visualization service and the querying service. A special focus is done on the latter service.

The 23rd International Conference on Information Integration and Web Intelligence

The 23rd International Conference on Information Integration and Web Intelligence

In order to achieve efficient interoperability of information systems, ontologies play an importa... more In order to achieve efficient interoperability of information systems, ontologies play an important role in resolving semantic heterogeneity. We propose a general interoperability architecture that uses ontologies for explicit description of the semantics of information sources, and web services to facilitate the communication between the different components of the architecture. It consists of 1) data provider services for mapping information sources to local source ontologies, 2) a knowledge base for representing reference domain ontology, and 3) several web services for encapsulating the different functionalities of the architecture. In this paper, we focus on a component of the architecture which is a tool, called DB2OWL, that automatically generates ontologies from database schemas as well as mappings that relate the ontologies to the information sources. The mapping process starts by detecting particular cases for conceptual elements in the database and accordingly converts da...

Schema decomposition is a well known method for logical database design. Decomposition mainly aim... more Schema decomposition is a well known method for logical database design. Decomposition mainly aims at redundancy reduction and elimination of anomalies. A good decomposition should preserve dependencies and maintain recoverability of information. We propose a semi-automatic method for decomposing a relational schema in an interactive way. A database designer can build the subschemes step-by-step, guided by quantitative measures of decomposition “goodness”. At each step, a ranked set of recommendations are provided to the designer to guide him to the next possible actions that lead to a better design.

Proceedings of the 21st International Conference on Information Integration and Web-based Applications & Services, 2019

In this paper, we present an approach for classifying movie genres based on user-ratings. Our app... more In this paper, we present an approach for classifying movie genres based on user-ratings. Our approach is based on collaborative filtering (CF), a common technique used in recommendation systems, where the similarity between movies based on user-ratings, is used to predict the genres of movies. The results of conducted experiments show that our genres classification approach outperforms many existing approaches, by achieving an F1-score of 0.70, and a hit-rate of 94%.

arXiv (Cornell University), Mar 12, 2024

Technology-facilitated gender-based violence has become a global threat to women's political repr... more Technology-facilitated gender-based violence has become a global threat to women's political representation and democracy. Understanding how online hate affects its targets is thus paramount. We analyse 10 million tweets directed at female candidates in the Brazilian election in 2022 and examine their reactions to online misogyny. Using a self-trained machine learning classifier to detect Portuguese misogynistic tweets and a quantitative analysis of the candidates' tweeting behaviour, we investigate how the number of misogynistic attacks received alters the online activity of the female candidates. We find that young and left-wing candidates and candidates with higher visibility online received significantly more attacks. Furthermore, we find that an increase in misogynistic attacks in the previous week is associated with a decrease in female candidates' tweets in the following week. This potentially threatens their equal participation in public opinion building and silences women's voices in political discourse.

Lecture Notes in Computer Science, 2022

Social Network Analysis and Mining, Jul 10, 2021

The history of intellectuals consists of a complex web of influences and interconnections of phil... more The history of intellectuals consists of a complex web of influences and interconnections of philosophers, scientists, writers, their work, and ideas. To understand how did these influences evolve over time, we mined a network of influence of over 12,500 intellectuals, enriched it with a temporal dimension dividing the history into six eras. We analyze time-sliced projections of the network into within-era, inter-era, and accumulated-era networks, and identify various patterns of intellectuals and eras and studied their development in time. We also construct influence cascades, analyze their properties: size, depth and breadth, and analyze how the cascades of influence evolve over the consecutive eras. We find out that the cascades are clustered into two categories, namely small-and large cascades. An interesting finding here is that the fraction of small cascades increases, while the fraction of larges cascades decreases over time. We also briefly analyze the community structure within the influence network of scholars.

The history of intellectuals consists of a complicated web of influences and interconnections of ... more The history of intellectuals consists of a complicated web of influences and interconnections of philosophers, scientists, writers, their work, and ideas. How did these influences evolve over time? Who were the most influential scholars in a period? To answer these questions, we mined a network of influence of over 12,500 intellectuals, extracted from the Linked Open Data provider YAGO. We enriched this network with a longitudinal perspective, and analysed time-sliced projections of the complete network differentiating between within-era, inter-era, and accumulated-era networks. We thus identified various patterns of intellectuals and eras, and studied their development in time. We show which scholars were most influential in different eras, and who took prominent knowledge broker roles. One essential finding is that the highest impact of an era's scholar was on their contemporaries, as well as the inter-era influence of each period was strongest to its consecutive one. Further, we see quantitative evidence that there was no re-discovery of Antiquity during the Renaissance, but a continuous reception since the Middle Ages.

Social Network Analysis and Mining, Jun 7, 2022

Negative word-of-mouth is a strong consumer and user response to dissatisfaction. Moral outrages ... more Negative word-of-mouth is a strong consumer and user response to dissatisfaction. Moral outrages can create an excessive collective aggressiveness against one single argument, one single word, or one action of a person resulting in hateful speech. In this work, we examine the change of vocabulary to explore the outbreak of online firestorms on Twitter. The sudden change of an emotional state can be captured in language. It reveals how people connect with each other to form outrage. We find that when users turn their outrage against somebody, the occurrence of self-referencing pronouns like 'I' and 'me' reduces significantly. Using data from Twitter, we derive such linguistic features together with features based on retweets and mention networks to use them as indicators for negative word-of-mouth dynamics in social media networks. Based on these features, we build three classification models that can predict the outbreak of a firestorm with high accuracy.

Intellectuals, scholars, philosophers, writers, and scientists, and their work are embedded in a ... more Intellectuals, scholars, philosophers, writers, and scientists, and their work are embedded in a long history of ideas. These traditions disseminated and diffused over a long history spanning from Greek-Roman antiquity to recent times. But how did those lines of traditions and influence of thoughts develop over the ages? How did intellectuals influence each other? What is the most far-reaching impact of influence, as well as who are the most immediate influencing, and the most influenced by other intellectuals in history? To answer these types of questions, we mined a network of influence among over 12 thousand intellectuals, from YAGO, a pioneering data source of Linked Open Data. We conducted several essential types of social network analysis, concerning connectivity, degree distribution, prestige (influence), and importance (centrality). We studied the diffusion dynamics of influence by analyzing the influence cascades in terms of size, depth and breadth. One interesting finding is the identification of two major, disjoint categories of small and large cascades of influence.

Virtual teams are becoming increasingly important. Since they are digital in nature, their "trace... more Virtual teams are becoming increasingly important. Since they are digital in nature, their "trace data" enable a broad set of new research opportunities. Online Games are especially useful for studying social behavior patterns of collaborative teams. In our study we used longitudinal data from the Massively Multiplayer Online Game (MMOG) Travian collected over a 12month period that included 4,753 teams with 18,056 individuals and their communication networks. For predicting team performance, we selected 13 SNA-based attributes frequently used in team and leadership research. Using machine learning algorithms, the added explanatory power derived from the patterns of the communication networks enabled us to achieve an adjusted R 2 = 0.67 in the best fitting performance prediction model and a prediction accuracy of up to 95.3% in the classification of top performing teams.

Social Networks, 2022

Abstract In multilayer networks, quantifying layer similarity is of great importance for many app... more Abstract In multilayer networks, quantifying layer similarity is of great importance for many applications. Traditional approaches to measure layer similarities rely mainly on micro-level features of network structures, such as node degree. In this paper, we propose to use mesoscopic network structures, i.e., communities, to assess layer similarity. Our proposed approach is based on matching the communities detected at the layers being compared. The similarity is thus defined using clustering evaluation methods such as purity and F-measure. Our results on empirical datasets show that the proposed approach provides more consistent layer taxonomies than other approaches.

2022 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM)

Lecture Notes in Computer Science, 2022

2018 14th International Conference on Signal-Image Technology & Internet-Based Systems (SITIS)

We propose a semantic-based methodology for Social Network Analysis (SNA). This methodology addre... more We propose a semantic-based methodology for Social Network Analysis (SNA). This methodology addresses computations needed for SNA in a declarative way -in contrast to traditional SNA where computations are procedural. Our ingredients are semantic technologies: We define an ontology to represent graphs, their components (nodes, edges or paths), and the structural relationships between these components. We exploit reasoning capabilities of ontologies to infer structural relations between graph components. We also use ontological queries to perform computations needed in SNA. To demonstrate how does this approach work, we present three showcases of typical network analysis: basic metrics, triadic census, and betweenness centrality. The proposed approaches offer several computational opportunities for analyzing networks with respect to calculation of path-dependent centrality metrics, e.g. in distributed setups.

Social Network Analysis and Mining

Negative word-of-mouth is a strong consumer and user response to dissatisfaction. Moral outrages ... more Negative word-of-mouth is a strong consumer and user response to dissatisfaction. Moral outrages can create an excessive collective aggressiveness against one single argument, one single word, or one action of a person resulting in hateful speech. In this work, we examine the change of vocabulary to explore the outbreak of online firestorms on Twitter. The sudden change of an emotional state can be captured in language. It reveals how people connect with each other to form outrage. We find that when users turn their outrage against somebody, the occurrence of self-referencing pronouns like ‘I’ and ‘me’ reduces significantly. Using data from Twitter, we derive such linguistic features together with features based on retweets and mention networks to use them as indicators for negative word-of-mouth dynamics in social media networks. Based on these features, we build three classification models that can predict the outbreak of a firestorm with high accuracy.

Online firestorms on Twitter are seemingly arbitrarily occurring outrages towards people, compani... more Online firestorms on Twitter are seemingly arbitrarily occurring outrages towards people, companies, media campaigns and politicians. Moral outrages can create an excessive collective aggressiveness against one single argument, one single word, or one action of a person resulting in hateful speech. With a collective "against the others" the negative dynamics often start. Using data from Twitter, we explored the starting points of several firestorm outbreaks. As a social media platform with hundreds of millions of users interacting in real-time on topics and events all over the world, Twitter serves as a social sensor for online discussions and is known for quick and often emotional disputes. The main question we pose in this article, is whether we can detect the outbreak of a firestorm. Given 21 online firestorms on Twitter, the key questions regarding the anomaly detection are: 1) How can we detect the changing point? 2) How can we distinguish the features that cause a mo...

The history of intellectuals consists of a complicated web of influences and interconnections of ... more The history of intellectuals consists of a complicated web of influences and interconnections of philosophers, scientists, writers, their work, and ideas. How did these influences evolve over time? Who were the most influential scholars in a period? To answer these questions, we mined a network of influence of over 12,500 intellectuals, extracted from the Linked Open Data provider YAGO. We enriched this network with a longitudinal perspective, and analysed time-sliced projections of the complete network differentiating between within-era, inter-era, and accumulated-era networks. We thus identified various patterns of intellectuals and eras, and studied their development in time. We show which scholars were most influential in different eras, and who took prominent knowledge broker roles. One essential finding is that the highest impact of an era's scholar was on their contemporaries, as well as the inter-era influence of each period was strongest to its consecutive one. Further,...

The growing amount of distributed data over the internet leads to increasing needs for interopera... more The growing amount of distributed data over the internet leads to increasing needs for interoperability. Being able to take into account the meaning of information is a real challenge for suitable data sharing. The semantic web and the ontologies are relevant technologies to provide semantic cooperation of heterogeneous sources. We propose a complete architecture OWSCIS (Ontology and Web Service based Cooperation of Information Sources) which allows to query a cooperation of information sources. The semantic of the local data is expressed using local ontologies which are mapped to a reference ontology. This reference ontology can be queried by an end user to transparently access the cooperation. The different components of the architecture are described: the data providers, the knowledge base, the interontology mapping process, the visualization service and the querying service. A special focus is done on the latter service.

The 23rd International Conference on Information Integration and Web Intelligence

The 23rd International Conference on Information Integration and Web Intelligence

In order to achieve efficient interoperability of information systems, ontologies play an importa... more In order to achieve efficient interoperability of information systems, ontologies play an important role in resolving semantic heterogeneity. We propose a general interoperability architecture that uses ontologies for explicit description of the semantics of information sources, and web services to facilitate the communication between the different components of the architecture. It consists of 1) data provider services for mapping information sources to local source ontologies, 2) a knowledge base for representing reference domain ontology, and 3) several web services for encapsulating the different functionalities of the architecture. In this paper, we focus on a component of the architecture which is a tool, called DB2OWL, that automatically generates ontologies from database schemas as well as mappings that relate the ontologies to the information sources. The mapping process starts by detecting particular cases for conceptual elements in the database and accordingly converts da...

Schema decomposition is a well known method for logical database design. Decomposition mainly aim... more Schema decomposition is a well known method for logical database design. Decomposition mainly aims at redundancy reduction and elimination of anomalies. A good decomposition should preserve dependencies and maintain recoverability of information. We propose a semi-automatic method for decomposing a relational schema in an interactive way. A database designer can build the subschemes step-by-step, guided by quantitative measures of decomposition “goodness”. At each step, a ranked set of recommendations are provided to the designer to guide him to the next possible actions that lead to a better design.

Proceedings of the 21st International Conference on Information Integration and Web-based Applications & Services, 2019

In this paper, we present an approach for classifying movie genres based on user-ratings. Our app... more In this paper, we present an approach for classifying movie genres based on user-ratings. Our approach is based on collaborative filtering (CF), a common technique used in recommendation systems, where the similarity between movies based on user-ratings, is used to predict the genres of movies. The results of conducted experiments show that our genres classification approach outperforms many existing approaches, by achieving an F1-score of 0.70, and a hit-rate of 94%.