388 research outputs found
Spiritual polarisation on social media: the case of Arab atheists on Twitter
No full textSocial media platforms provide an unprecedented method of communication, and they are considered an integral part of people's lifestyles. Also, these platforms facilitate forming communities, groups and networks. Hence, it attracted researchers to study people's interactions and analyse the enormous human-generated data. In this thesis, I focus on studying the online Arab communities as a case study of online communities to understand online spiritual-based groups and the polarisation among them. This work combines multi-disciplinary approaches of natural language processing, information retrieval, data science and social and technological networks to understand better the online social behaviour of Arabs with different religious beliefs. I explore the discussion among Arab Twitter users from religious and atheistic groups. I identify four types of Twitter users based on how they describe themselves: Atheistic, Theistic, Tanweeri (reformers), and Rationalists. This study shows that Arabs from different religious spectrums get involved in online discussions on local and regional topics.
I collected two datasets from Twitter for users who discussed religions and atheism, in which I considered about 434 accounts in the first dataset and 2,673 accounts in the second one. The analysis shows that, whatever their attitude towards religions, Arab Twitter users tend to use their accounts to promote their beliefs and to show their stances towards others. I showed that the data that was generated by these four groups illustrate the rich socio-cultural context in which discussions among believers, non-believers and religious reformers unfold. I showed that there is a clear online polarisation between atheists and theists, while Rationalist and Tanweeri accounts are spread among and between the two polarised groups. Arab atheists are separated into two groups in terms of engagement based on the accounts they prefer to interact-with.
I found that Arab atheists and theists mention and reply-to users from any religious groups and vice versa, but they tend to retweet and follow accounts from their own group. The findings of this thesis provide insights for researchers to understand the case study of Arab online communities and the religious and non-religious online polarisation. Also, it shows the implications for the studies of spiritual discourse on social media and provides a better cross-cultural understanding of relevant aspects
Enriching lexicons for better social media analysis
No full textLexicons are indispensable tools for textual analysis, offering valuable insights through labelled
term associations. Despite their utility, traditional lexicons face significant challenges
in keeping up with the rapid evolution of language, particularly in informal contexts that are
common in social media. Static lexicons often fail to capture new terms and shifting word
usages, leading to gaps in coverage and potential inaccuracies in analysis tasks. This thesis
explores lexicon expansion to address these challenges, leveraging socially sourced dictionaries
such as Urban Dictionary and Wiktionary to enhance lexicon coverage and relevance.
Terms from these dictionaries are utilized as candidates for inclusion in various categories
within the lexicons.
The study is anchored in four research questions. First, it examines the utility of lexicons with
extensive category coverage in analysing user cohorts on social media. Second, it investigates
the feasibility of expanding lexicons using noisy, socially curated dictionaries. Third, it
evaluates the impact of lexicon and dictionary properties such as size, structure, and noise
levels on the quality of expansions. Lastly, it assesses the added value of expanded lexicons
in downstream analysis tasks.
Key contributions include the introduction of the “Cohort Analysis” task, derived from social
media text, to analyse how different cohorts relate various concepts. The thesis also presents
“Lexpansion”, a tool for lexicon expansion and comparative analysis of lexicon-dictionary
pairs. Using this tool, the study demonstrates that socially sourced dictionaries can effectively
enhance lexicons, even when noisy. The expanded lexicons are shown to yield new,
actionable insights, validated by comparing findings from original and expanded lexicons in
cohort analysis tasks.
The results affirm that automated lexicon expansion can significantly improve the coverage
and relevance of lexicons in dynamic linguistic environments, enabling more robust and nuanced
social media analysis. These findings underscore the continued importance of lexicons,
even in the era of large language models, as they remain crucial for interpretable, domainspecific
analysis
Arabic sarcasm detection
No full textSarcasm is a form of verbal irony that is often used to express ridicule or contempt. When using sarcasm, a speaker expresses their opinion in an indirect way, where the literal meaning is different from the intended one. Additionally, sarcasm is a sociolinguistic tool that people use to express themselves and it reflects their cultural and social background. Sarcasm detection refers to the process of automatically and computationally identifying whether a piece of text is sarcastic. This has been well studied in the context of English, but Arabic lags behind. In this thesis, we try to fill in the gaps in the research on Arabic sarcasm detection.
First, we start by exploring approaches to create an Arabic sarcasm dataset. We create ArSarcasm dataset through the re-annotation of existing sentiment analysis datasets. These labels represent perceived sarcasm as the labels reflect the annotators' perception. The analysis shows that sarcasm is prominent in the used sentiment datasets, with 16% of the sentences being sarcastic. Our experiments show that sarcasm is disruptive for sentiment analysers. Analysis shows that annotating subjective content can be challenging and prone to biases.
Second, to mitigate the issues and fallbacks of sarcasm data collection approaches, we propose to collect sarcasm datasets by asking people to label their words, which is referred to as intended sarcasm. The resulting dataset, which is first-party annotated, would have more reliable and trustworthy labels and does not have the issues of third-party annotated data.
Next, we test state-of-the-art machine learning models on the newly created datasets. Those experiments provide a benchmark for these datasets. The experiments show that intended sarcasm detection is more challenging than perceived sarcasm detection. Also, the experiments show that monolingual Arabic language models, which include dialects in their pre-training data, perform better on the sarcasm detection task. Additionally, we provide the details of shared tasks that utilise the new datasets.
Finally, we provide an in-depth error analysis comparing humans' performance in sarcasm detection against the performance of state-of-the-art models. Our analysis confirms that sarcasm is challenging for both humans and machines. We also highlight the features and patterns used to express sarcasm, such as idioms and proverbs. When extending the analysis to focus on Arabic dialects, we found that dialect familiarity affects how Arabic speakers understand and interpret sarcasm. Arabic speakers were better able to detect sarcasm expressed in their dialect or one they were familiar with
Stance characterization and detection on social media
No full textStance detection refers to the task of identifying a viewpoint as either supporting or
opposing a given topic. The current research on socio-political opinion mining on
social media is still in its infancy. Most computational approaches in this field are
limited to the independent use of textual elements of a user’s posts from social factors
such as homophily and network structure. This thesis provides a thorough study of
stance detection on social media and assesses various online signals to identify the
stance and understand its association with the analysed topic. We explore the task of
detecting stance on Twitter, which is a well-known social media platform where people
often express stance implicitly or explicitly.
First, we examine the relation between sentiment and stance and analyse the inter-play between sentiment polarity and expressed stance. For this purpose, we extend the
current SemEval stance dataset by annotating tweets related to four new topics with
sentiment and stance labels. Then, we evaluate the effectiveness of sentiment analysis
methods on stance prediction using two stance datasets.
Second, we examine the multi-modal representation of stance on social media by
evaluating multiple stance detection models using textual content and online interactions. The finding of this chapter suggests that using social interactions along with
other textual features can improve the stance detection model. Moreover, we show
how an unconscious social interaction can reveal the stance.
Next, we design an online framework to preserve users’ privacy concerning the
implicitly inferred stance on social media. Thus, we evaluate the effectiveness of the
two stance obfuscation methods and use different stance detection models to measure
the overall performance of the proposed framework.
Finally, we study the dynamics of polarized stance to understand the factors that
influence online stance. Particularly, we extend the analysis of online stance signals
and examine the interplay between stance and automated accounts (bots). Furthermore,
we pose the problem of gauging the bots’ effect on polarized stance through a sole
focus on the diffusion of bots on the online social network
Computational sarcasm detection and understanding in online communication
No full textThe presence of sarcasm in online communication has motivated an increasing number of computational investigations of sarcasm across the scientific community. In this thesis, we build upon these investigations. Pointing out their limitations, we bring four contributions that span two research directions: sarcasm detection and sarcasm understanding.
Sarcasm detection is the task of building computational models optimised for recognising sarcasm in a given text.
These models are often built in a supervised learning paradigm, relying on datasets of texts labelled for sarcasm.
We bring two contributions in this direction.
First, we question the effectiveness of previous methods used to label texts for sarcasm. We argue that the labels they produce might not coincide with the sarcastic intention of the authors of the texts that they are labelling.
In response, we suggest a new method, and we use it to build iSarcasm, a novel dataset of sarcastic and non-sarcastic tweets.
We show that previous models achieve considerably lower performance on iSarcasm than on previous datasets, while human annotators achieve a considerably higher performance, compared to models, pointing out the need for more effective models.
Therefore, as a second contribution, we organise a competition that invites the community to create such models.
Sarcasm understanding is the task of explicating the phenomena that are subsumed under the umbrella of sarcasm through computational investigation.
We bring two contributions in this direction.
First, we conduct an alaysis into the socio-demographic ecology of sarcastic exchanges between human interlocutors. We find that the effectiveness of such exchanges is influenced by the socio-demographic similarity between the interlocutors, with factors such as English language nativeness, age, and gender, being particualry influential. We suggest that future social analysis tools should account for these factors.
Second, we challenge the motivation of a recent endeavour of the community; mainly, that of augmenting dialogue systems with the ability to generate sarcastic responses. Through a series of social experiments, we provide guidelines for dialogue systems concerning the appropriateness of generating sarcastic responses, and the formulation of such responses.
Through our work, we aim to encourage the community to consider computational investigations of sarcasm interdisciplinarily, at the intersection of natural language processing and computational social science
An efficient method for using machine translation technologies in cross-language patent search
No full textTopics in prior-art patent search are typically full patent
applications and relevant items are patents often taken from sources in different languages. Cross language patent retrieval (CLPR) technologies support searching for relevant patents across multiple languages. As such, CLPR requires a translation process between topic and document languages. The most popular method for crossing the language barrier in cross language information retrieval (CLIR) in general is machine translation (MT). High quality MT systems are becoming widely available for many language pairs and generally have higher effectiveness for CLIR than dictionary based methods. However for patent search, using MT for translation of the very long search queries requires
significant time and computational resources. We present a novel MT approach specifically designed for CLIR in general and CLPR in particular. In this method information retrieval (IR) text pre-processing in the form of stop word removal and stemming are applied to the MT training corpus prior to the training phase of the MT system. Applying this step leads to a significant decrease in the MT computational and resource requirements in both the training and translation phases. Experiments on the CLEF-IP 2010 CLPR task show the new technique to be 5 to 23 times faster than standard MT for query translation, while maintaining statistically indistinguishable IR effectiveness. Furthermore the new method is significantly better than standard MT when only limited translation training resources are available
Toward higher effectiveness for recall-oriented information retrieval: A patent retrieval case study
No full textResearch in information retrieval (IR) has largely been directed towards tasks requiring high precision. Recently, other IR applications which can be described as recall-oriented IR tasks have received increased attention in the IR research domain. Prominent among these IR applications are patent search and legal search, where users are typically ready to check hundreds or possibly thousands of documents in order to find any possible relevant document. The main concerns in this kind of application are very different from those in standard precision-oriented IR tasks, where users tend to be focused on finding an answer to their information need that can typically be addressed by one or two relevant documents. For precision-oriented tasks, mean average precision continues to be used as the primary evaluation metric for almost all IR applications. For recall-oriented IR applications the nature of the search task, including objectives, users, queries, and document collections, is different from that of standard precision-oriented search tasks. In this research study, two dimensions in IR are explored for the recall-oriented patent search task. The study includes IR system evaluation and multilingual IR for patent search. In each of these dimensions, current IR techniques are studied and novel techniques developed especially for this kind of recall-oriented IR application are proposed and investigated experimentally in the context of patent retrieval. The techniques developed in this thesis provide a significant contribution toward evaluating the effectiveness of recall-oriented IR in general and particularly patent search, and improving the efficiency of multilingual search for this kind of task
A study of query expansion methods for patent retrieval
No full textPatent retrieval is a recall-oriented search task where the objective is to find all possible relevant documents. Queries in patent retrieval are typically very long since they take the form of a patent claim or even a full patent application in the case of priorart patent search. Nevertheless, there is generally a significant mismatch between the query and the relevant documents, often leading to low retrieval effectiveness. Some previous work has
tried to address this mismatch through the application of query expansion (QE) techniques which have generally showed
effectiveness for many other retrieval tasks. However, results of QE on patent search have been found to be very disappointing. We present a review of previous investigations of QE in patent retrieval, and explore some of these techniques on a prior-art patent search task. In addition, a novel method for QE using automatically generated synonyms set is presented. While previous QE techniques fail to improve over baseline retrieval, our new approach show statistically better retrieval precision over
the baseline, although not for recall. In addition, it proves to be significantly more efficient than existing techniques. An extensive analysis to the results is presented which seeks to better understand situations where these QE techniques succeed or fail
Applying the KISS principle for the CLEF-IP 2010 prior art candidate patent search task
No full textWe present our experiments and results for the DCU CNGL
participation in the CLEF-IP 2010 Candidate Patent Search Task. Our work applied standard information retrieval (IR) techniques to patent search. In addition, a very simple citation extraction method was applied to improve the
results. This was our second consecutive participation in the CLEF-IP tasks. Our experiments in 2009 showed that many sophisticated approach to IR do not improve the retrieval effectiveness for this task. For this reason of we decided
to apply only simple methods in 2010. These were demonstrated to be highly competitive with other participants. DCU submitted three runs for the Prior Art
Candidate Search Task, two of these runs achieved the second and third ranks among the 25 runs submitted by nine different participants. Our best run achieved MAP of 0.203, recall of 0.618, and PRES of 0.523
Arabic dialect identification under scrutiny:Limitations of single-label classification
No full textAutomatic Arabic Dialect Identification (ADI) of text has gained great popularity since it was introduced in the early 2010s. Multiple datasets were developed, and yearly shared tasks have been running since 2018. However, ADI systems are reported to fail in distinguishing between the micro-dialects of Arabic. We argue that the currently adopted framing of the ADI task as a single-label classification problem is one of the main reasons for that. We highlight the limitation of the incompleteness of the Dialect labels and demonstrate how it impacts the evaluation of ADI systems. A manual error analysis for the predictions of an ADI, performed by 7 native speakers of different Arabic dialects, revealed that ≈ 67% of the validated errors are not true errors. Consequently, we propose framing ADI as a multi-label classification task and give recommendations for designing new ADI datasets
- …
