During the 2023–ongoing Gaza war, Palestinian advocacy on social media has faced rapid removals, downranking, and account sanctions. In this contribution, we offer a layered analysis of how people endure and counter this repression across affective, mechanistic, and material dimensions. Using patchwork ethnography over 295 first-person testimonies and 85 NGO/press documents, we identify a recursive Contest Loop: hostile mass-report brigades and automated enforcement that spur supporter “appeal brigades,” mirroring, and migration. Findings are organized as a three-layer ecology—Invisible Scars (whiplash, shadowbanning as probabilistic throttling, self-censorship), Dueling Brigades (frictions, coordinated reports, supporter procedures), and Feed-to-Street Ripples (fundraising, evidentiary preservation, livelihoods). Conceptually, we extend platform-assemblage thinking with a Resistance Assemblage: ad-hoc technical, emotional, and legal mutual-aid infrastructures that keep visibility alive under sanction. We contribute: (1) an event-centered, experience-near account of co-produced moderation in conflict; (2) two integrative lenses (Contest Loop, Resistance Assemblage); and (3) design/policy directions, including collective-appeal dashboards, and evidentiary safeguards that separate archiving from distribution.

Religion is a main aspect of life in many parts of the world; hence, it acts as a powerful tool for influencing people’s views and actions. In the context of propaganda and misinformation, religion has been perceived as a factor that impacts people negatively leading them to be influenced by false or biased information. However, there are limited quantitative studies that explore the exact role of religion in this process. In this study, we investigate whether state-sponsored propaganda accounts share religious content in a different way than the typical norms reported in the literature and whether they mobilize this content to promote their agendas. We find by exploring 15 Middle Eastern propaganda Twitter datasets encompassing around 124 million tweets from 32.5K accounts that propagandists share religious texts according to patterns that reflect aspects of their state’s agenda. We also demonstrate examples where such texts were used to modulate political messages.

Variants of Persian (Farsi, Dari, and Tajiki) are spoken by more than 110 million people worldwide. Despite the growing interest in broadening the coverage of Natural Language Processing (NLP) methods, Persian has received limited attention. This survey addresses this gap by reviewing over 200 peer-reviewed studies published across the last two decades, documenting more than 40 publicly available corpora, and analysing linguistic challenges, pipelines, and applications across approaches ranging from rule-based methods to Large Language Models (LLMs). Given the rapid advancement of LLMs, we study the state of Persian-specific models across different tasks, review the available LLMs for Persian, assess their performance and limitations, and provide a comprehensive discussion of their strengths and gaps. Our analysis shows that although attention to Persian NLP has increased and notable progress has been made, critical gaps remain—particularly the scarcity of standardised benchmarks and gold corpora in tasks such as toxicity and safety, bias and fairness, and explainability and reasoning. Future progress requires expanding culturally grounded datasets, establishing robust evaluation frameworks, and fostering open-source collaboration and shared-task participation to accelerate the development of Persian NLP.

Toxic language detection is crucial for creating safer online environments and limiting the spread of harmful content. While toxic language detection has been under-explored in Persian, the current work compares different methods for this task, including fine-tuning, data enrichment, zero-shot and few-shot learning, and cross-lingual transfer learning. What is especially compelling is the impact of cultural context on transfer learning for this task: We show that the language of a country with cultural similarities to Persian yields better results in transfer learning. Conversely, the improvement is lower when the language comes from a culturally distinct country.

Arabic has diverse dialects, where one dialect can be substantially different from the others.In the NLP literature, some assumptions about these dialects are widely adopted (e.g., "Arabic dialects can be grouped into distinguishable regional dialects") and are manifested in different computational tasks such as Arabic Dialect Identification (ADI).However, these assumptions are not quantitatively verified.We identify four of these assumptions and examine them by extending and analyzing a multi-label dataset, where the validity of each sentence in 11 different country-level dialects is manually assessed by speakers of these dialects.Our analysis indicates that the four assumptions oversimplify reality, and some of them are not always accurate.This in turn might be hindering further progress in different Arabic NLP tasks.

Nascent research on human-computer interaction concerns itself with fairness of content moderation systems. Designing globally applicable content moderation systems requires considering historical, cultural, and socio-technical factors. Inspired by this line of work, we investigate Arab users' perception of Facebook's moderation practices. We collect a set of 448 deleted Arabic posts, and we ask Arab annotators to evaluate these posts based on (a) Facebook Community Standards (FBCS) and (b) their personal opinion. Each post was judged by 10 annotators to account for subjectivity. Our analysis shows a clear gap between the Arabs' understanding of the FBCS and how Facebook implements these standards. The study highlights a need for discussion on the moderation guidelines on social media platforms about who decides the moderation guidelines, how these guidelines are interpreted, and how well they represent the views of marginalised user communities.

Hadith, the recorded words and actions of the prophet Muhammad, is a key source of the instructions and foundations of Islam, alongside the Quran. Interpreting individual hadiths and verifying their authenticity can be difficult, even controversial, and the subject has attracted the attention of many scholars who have established an entire science of Hadith criticism. Recent quantitative studies of hadiths focus on developing systems for automatic classification, authentication, and information retrieval that operate over existing hadith compilations. Qualitative studies on the other hand try to discuss different social and political issues from the perspective of hadiths, or they inspect how hadiths are used in specific contexts in official communications and press releases for argumentation and propaganda. However, there are no studies that attempt to understand the actual presence of hadiths among Muslims in their daily lives and interactions. In this study, we try to fill this gap by exploring the presence of hadiths on Twitter from January 2019 to January 2023. We highlight the challenges that quantitative methods should consider while processing texts that include hadiths and we provide a methodology for Islamic scholars to validate their hypotheses about hadiths on big data that better represent the position of the society and Hadith influence

The detection and analysis of fake news and its origins has become a main task associated with the overall objective of social media regulation in recent years. The majority of work has been dedicated towards detecting misinformation with some focus on analyzing the flow of fake news across social networks. However, there is less attention to the characteristics of social media users who consume this fake news. In this work, we investigate the possibility of predicting users' reactions towards fake news and defining some network characteristics for each users' group. We utilized a set of fact-checking websites in the Arab world that report social media posts spreading fake news and the interactions with them. We defined three sets of users: 1) Spreaders, who spread fake news, 2) Checkers, who constantly share fact-checking threads, and 3) Refuters, who respond to fake-news posts declaring their inaccuracy. We build a classifier that uses users' network graph to predict their reactions with an accuracy exceeding 93%. We applied further analysis for the most significant features of each users group and noticed that spreaders interact with more accounts that use their mother tongue, a considerable number of famous state-sponsored accounts, and accounts that get suspended while checkers and refuters interact with more foreign accounts and news-reporting entities. Central nodes in the networks of spreaders were found to be linked with state-sponsored media, whereas central nodes in the networks of checkers included organizations with a cross-cultural nature.

Social media platforms like Twitter provide rich data that can offer insights into various aspects of users' behavior. In this study, we explore the potential of emoji usage as a means for demographic prediction. Leveraging a Twitter dataset of 18,689 users, annotated with gender and ethnicity labels, we analyze the proportion of tweets containing emoji across different demographic groups. We identify significant variations in emoji usage, with women utilizing emoji more frequently than men and users of African descent displaying a higher tendency for emoji usage compared to users of European descent. Moreover, we investigate the most distinctive emoji for each group, revealing intriguing patterns that are closely tied to the cultural and demographic backgrounds of users. Building upon these findings, we employ machine learning models with different feature extraction techniques to predict users' gender and ethnicity. Our results demonstrate the predictive power of emoji, outperforming traditional text-based features. Furthermore, our study provides evidence that emoji usage can be a valuable resource for inferring user demographic characteristics on social media platforms, contributing to our understanding of user behavior in digital environments.

Transcribed speech and user-generated text in Arabic typically contain a mixture of Modern Standard Arabic (MSA), the standardized language taught in schools, and Dialectal Arabic (DA), used in daily communications.To handle this variation, previous work in Arabic NLP has focused on Dialect Identification (DI) on the sentence or the token level.However, DI treats the task as binary, whereas we argue that Arabic speakers perceive a spectrum of dialectness, which we operationalize at the sentence level as the Arabic Level of Dialectness (ALDi), a continuous linguistic variable.We introduce the AOC-ALDi dataset (derived from the AOC dataset), containing 127,835 sentences (17% from news articles and 83% from user comments on those articles) which are manually labeled with their level of dialectness.We provide a detailed analysis of AOC-ALDi and show that a model trained on it can effectively identify levels of dialectness on a range of other corpora (including dialects and genres not included in AOC-ALDi), providing a more nuanced picture than traditional DI systems.Through case studies, we illustrate how ALDi can reveal Arabic speakers' stylistic choices in different situations, a useful property for sociolinguistic analyses.

Twitter accounts are public by default, but Twitter gives the option to create protected accounts, where only approved followers can see their tweets. The publicly visible information changes based on the account type and the visibility of tweets also depends solely on the poster's account type which can cause unintended disclosures especially when users interact. We surveyed 336 Twitter users to understand users' awareness of account information visibility, as well as the tweet visibility when users interact. We find that our participants are aware of the visibility of their profile information and individual tweets. However, the visibility of followed topics, lists, and interactions with protected accounts is confusing. Only 31% of the participants were aware that a reply by a public account to a protected account's tweet would be publicly visible. Surprisingly, having a protected account does not result in a better understanding of the account information or tweet visibility.

Previous sarcasm generation research has focused on how to generate text that people perceive as sarcastic to create more human-like interactions.In this paper, we argue that we should first turn our attention to the question of when sarcasm should be generated, finding that humans consider sarcastic responses inappropriate to many input utterances.Next, we use a theory-driven framework for generating sarcastic responses, which allows us to control the linguistic devices included during generation.For each device, we investigate how much humans associate it with sarcasm, finding that pragmatic insincerity and emotional markers are devices crucial for making sarcasm recognisable.

On behalf of all the members of the organizing Committee, we are pleased to welcome all of you to IEEE/ACM ASONAM 2022.

Changing a Twitter account’s privacy setting between public and protected changes the visibility of past tweets. By inspecting the privacy setting of more than 100K Twitter users over 3 months, we noticed that over 40% of those users changed their privacy setting at least once with around 16% changing it over 5 times. This observation motivated us to explore the reasons why people switch their privacy settings. We studied these switching phenomena quantitatively by comparing the tweeting behaviour of users when public vs protected, and qualitatively using two follow-up surveys (n=100, n=324) to understand potential reasoning behind the observed behaviours. Our quantitative analysis shows that users who switch privacy settings mention others and share hashtags more when their setting is public. Our surveys highlighted that users turn protected to share personal content and regulate boundaries while they turn public to interact with others in ways the protected setting prevents.

Aspect Based Sentiment Analysis is a dominant research area with potential applications in social media analytics, business, finance, and health.Prior works in this area are primarily based on supervised methods, with a few techniques using weak supervision limited to predicting a single aspect category per review sentence.In this paper, we present an extremely weakly supervised multi-label Aspect Category Sentiment Analysis framework which does not use any labelled data.We only rely on a single word per class as an initial indicative information.We further propose an automatic word selection technique to choose these seed categories and sentiment words.We explore unsupervised language model post-training to improve the overall performance, and propose a multi-label generator model to generate multiple aspect category-sentiment pairs per review sentence.Experiments conducted on four benchmark datasets showcase our method to outperform other weakly supervised baselines by a significant margin. 1

In this study, we investigate the extent of polarisation among theist versus atheist groups on Arab Twitter and their networks. We find four main self-identified groups of Arab users that can be distinguished by different attitudes to religion. In addition to Atheists and Theists, there are Rationalists, who promote rational thinking regardless of religious affiliation, and Tanweeri, who promote religious reforms. Through a keyword search of Twitter account handles and biographies, we identified 2,673 active, public Twitter accounts that clearly state whether they are Atheists, Theists, Tanweeri or Rationalists and analysed the interactions among themselves and the accounts that are followed, retweeted, or mentioned the most in their networks. Depending on the network analysed, we found between four and seven sub-communities that highlight the rich socio-cultural context in which discussions of religion, non-religion, and religious reform unfold. While there was clear online polarisation between atheists and theists, Rationalist and Tanweeri accounts are spread among the two polarised sides, acting as natural bridges. We also found a clear separation between Arab atheists who engage with Arab accounts promoting atheism and those who primarily engage with Western accounts promoting atheism. We discuss implications for the study of religious debate and religious polarisation on social media.

Research in sociology and linguistics shows that people use language not only to express their own identity but to understand the identity of others. Recent work established a connection between expression of identity and emoji usage on social media, through use of emoji skin tone modifiers. Motivated by that finding, this work asks if, as with language, readers are sensitive to such acts of self-expression and use them to understand the identity of authors. In behavioral experiments (n=488), where text and emoji content of social media posts were carefully controlled before being presented to participants, we find in the affirmative - emoji are a salient signal of author identity. That signal is distinct from, and complementary to, the one encoded in language. Participant groups (based on self-identified ethnicity) showed no differences in how they perceive this signal, except in the case of the default yellow emoji. While both groups associate this with a White identity, the effect was stronger in White participants. Our finding that emoji can index social variables will have experimental applications for researchers but also implications for designers: supposedly neutral defaults may be more representative of some users than others.

We consider the distinction between intended and perceived sarcasm in the context of textual sarcasm detection.The former occurs when an utterance is sarcastic from the perspective of its author, while the latter occurs when the utterance is interpreted as sarcastic by the audience.We show the limitations of previous labelling methods in capturing intended sarcasm and introduce the iSarcasm dataset of tweets labeled for sarcasm directly by their authors.Examining the state-of-theart sarcasm detection models on our dataset showed low performance compared to previously studied datasets, which indicates that these datasets might be biased or obvious and sarcasm could be a phenomenon under-studied computationally thus far.By providing the iSarcasm dataset, we aim to encourage future NLP research to develop methods for detecting sarcasm in text as intended by the authors of the text, not as labeled under assumptions that we demonstrate to be sub-optimal.

The choice of the corpus on which word embeddings are trained can have a sizable effect on the learned representations, the types of analyses that can be performed with them, and their utility as features for machine learning models. To contribute to the existing sets of pre-trained word embeddings, we introduce and release the first set of word embeddings trained on the content of Urban Dictionary, a crowd-sourced dictionary for slang words and phrases. We show that although these embeddings are trained on fewer total tokens (by at least an order of magnitude compared to most popular pre-trained embeddings), they have high performance across a range of common word embedding evaluations, ranging from semantic similarity to word clustering tasks. Further, for some extrinsic tasks such as sentiment analysis and sarcasm detection where we expect to require some knowledge of colloquial language on social media data, initializing classifiers with the Urban Dictionary Embeddings resulted in improved performance compared to initializing with a range of other well-known, pre-trained embeddings that are order of magnitude larger in size.

While social media offer users a platform for self-expression, identity exploration, and community management, among other functions, they also offer space for religious practice and expression. In this paper, we explore social media spaces as they subtend new forms of religious experiences and rituals. We present a mixed-method study to understand the practice of sharing Quran verses on Arabic Twitter in their cultural context by combining a quantitative analysis of the most shared Quran verses, the topics covered by these verses, and the modalities of sharing, with a qualitative study of users' goals. This analysis of a set of 2.6 million tweets containing Quran verses demonstrates that online religious expression in the form of sharing Quran verses both extends offline religious life and supports new forms of religious expression including goals such as doing good deeds, giving charity, holding memorials, and showing solidarity. By analysing the responses on a survey, we found that our Arab Muslim respondents conceptualize social media platforms as everlasting, at least beyond their lifetimes, where they consider them to be effective for certain religious practices, such as reciting Quran, supplication (dua), and ceaseless charity. Our quantitative analysis of the most shared verses of the Quran underlines this commitment to religious expression as an act of worship, highlighting topics such as the hereafter, God's mercy, and sharia law. We note that verses on topics such as jihad are shared much less often, contradicting some media representation of Muslim social media use and practice.

Online social networks (OSN) play an essential role for connecting people and allowing them to communicate online. OSN users share their thoughts, moments, and news with their network. The messages they share online can include sarcastic posts, where the intended meaning expressed by the written text is different from the literal one. This could result in miscommunication. Previous research in psycholinguistics has studied the sociocultural factors the might lead to sarcasm misunderstanding between speakers and listeners. However, there is a lack of such studies in the context of OSN. In this paper we fill this gap by performing a quantitative analysis on the influence of sociocultural variables, including gender, age, country, and English language nativeness, on the effectiveness of sarcastic communication online. We collect examples of sarcastic tweets directly from the authors who posted them. Further, we ask third-party annotators of different sociocultural backgrounds to label these tweets for sarcasm. Our analysis indicates that age, English language nativeness, and country are significantly influential and should be considered in the design of future social analysis tools that either study sarcasm directly, or look at related phenomena where sarcasm may have an influence. We also make observations about the social ecology surrounding sarcastic exchanges on OSNs. We conclude by suggesting ways in which our findings can be included in future work.

We investigate the impact of using author context on textual sarcasm detection.We define author context as the embedded representation of their historical posts on Twitter and suggest neural models that extract these representations.We experiment with two tweet datasets, one labelled manually for sarcasm, and the other via tag-based distant supervision.We achieve state-of-the-art performance on the second dataset, but not on the one labelled manually, indicating a difference between intended sarcasm, captured by distant supervision, and perceived sarcasm, captured by manual labelling.

To what extent user's stance towards a given topic could be inferred? Most of the studies on stance detection have focused on analysing user's posts on a given topic to predict the stance. However, the stance in social media can be inferred from a mixture of signals that might reflect user's beliefs including posts and online interactions. This paper examines various online features of users to detect their stance towards different topics. We compare multiple set of features, including on-topic content, network interactions, user's preferences, and online network connections. Our objective is to understand the online signals that can reveal the users' stance. Experimentation is applied on tweets dataset from the SemEval stance detection task, which covers five topics. Results show that stance of a user can be detected with multiple signals of user's online activity, including their posts on the topic, the network they interact with or follow, the websites they visit, and the content they like. The performance of the stance modelling using different network features are comparable with the state-of-the-art reported model that used textual content only. In addition, combining network and content features leads to the highest reported performance to date on the SemEval dataset with F-measure of 72.49%. We further present an extensive analysis to show how these different set of features can reveal stance. Our findings have distinct privacy implications, where they highlight that stance is strongly embedded in user's online social network that, in principle, individuals can be profiled from their interactions and connections even when they do not post about the topic.

In this paper we present the second version of our multilingual tweet classification tool. ClassStrength v2 classifies tweets into 14 categories (Sports, Music, News&Politics etc.) using a distant supervision approach. The new version extends the initial set of five languages to ten (English, French, German, Chinese, Japanese, Arabic, Russian, Spanish, Portuguese and Polish). In addition, the classification models of each language get automatically updated every month to allow accurate classification over time. Our experimentation showed that the larger the time gap between the tweet and the data used for training the model, the worse the performance, which motivated for creating an adaptive version of ClassStrength that get its models updated periodically.

We analyze fifteen Twitter user geolocation models and two baselines comparing how they are evaluated. Our results demonstrate that the choice of effectiveness metric can have a substantial impact on the conclusions drawn from an experiment. We show that for general evaluations, a range of metrics should be reported to ensure that a complete picture of system effectiveness is conveyed.

Predicting the stance of social media users on a topic can be challenging, particularly for users who never express explicit stances. Earlier work has shown that using users' historical or non-relevant tweets can be used to predict stance. We build on prior work by making use of users' interaction elements, such as retweeted accounts and mentioned hashtags, to compute the similarities between users and to classify new users in a user similarity feature space. We show that this approach significantly improves stance prediction on two datasets that differ in terms of language, topic, and cultural background.

In this paper we present our multilingual tweet classification tool. ClassStrength provides a set of classification models in different languages that classify tweets into 14 general-purpose categories, including: sports, politics, entertainment, comedy, etc. Our classifier uses a distant-supervision approach for creating training data in any available language on Twitter. The classifier uses a soft-classification scheme, where it generates a likelihood score for a tweet to match each of the 14 categories. The initial version of our tool covers five languages, namely: English, Arabic, French, German, and Russian. More languages are to be covered in next releases. The classification model created for each language is generated from hundreds of thousands of training tweets. Our evaluation to the classifier shows superior accuracy compared to standard manual methods. Our reported accuracy is 84% based on crowd preferences over a balanced test set of English tweets covering all 14 classes.

Many adult content websites incorporate social networking features. Although these are popular, they raise significant challenges, including the potential for users to "catfish", i.e., to create fake profiles to deceive other users. This paper takes an initial step towards automated catfish detection. We explore the characteristics of the different age and gender groups, identifying a number of distinctions. Through this, we train models based on user profiles and comments, via the ground truth of specially verified profiles. When applying our models for age and gender estimation to unverified profiles, 38% of profiles are classified as lying about their age, and 25% are predicted to be lying about their gender. The results suggest that women have a greater propensity to catfish than men. Our preliminary work has notable implications on operators of such online social networks, as well as users who may worry about interacting with catfishes.

Languages with no standard orthographic representation faces a challenge to evaluate the output from Automatic Speech Recognition (ASR). Since the reference transcription text can vary widely from one user to another. We propose an innovative approach for evaluating speech recognition using Multi-References. For each recognized speech segments, we ask five different users to transcribe the speech. We combine the alignment for the multiple references, and use the combined alignment to report a modified version of Word Error Rate (WER). This approach is in favor of accepting a recognized word if any of the references typed it in the same form. Results are reported using two Dialectal Arabic (DA) as a language with no standard orthographic; Egyptian, and North African speech. The average WER for the five references individually is 71.4%, and 80.1% respectively. When considering all references combined, the Multi-References MR-WER was found to be 39.7%, and 45.9% respectively.

There is little doubt about whether social networks play a role in modern protests. This agreement has triggered an entire research avenue, in which social structure and content analysis have been central - but are typically exploited separately.

TweetMogaz is a news portal platform that generates news reports from social media content. It uses an adaptive information filtering technique for tracking tweets relevant to news topics, such as politics and sports in some regions. Relevant tweets for each topic are used to generate a comprehensive report about public reaction toward events happening. Showing a news report about an entire topic may be suboptimal for some users, since users prefer story-oriented presentation. In this demonstration, we present a technique for identifying stories within a stream of microblogs on a given topic. Detected tweets on a news story are used to generate a dynamic pseudo-article that gets its content updated in real-time based on trends on Twitter. Pseudo-article consists of a title, front-page image, set of tweets on the story, and links to external news articles. The platform is running live and tracks news on hot topics including Egyptian politics, Syrian conflict, and international sports.

Over the past years, Twitter has earned a growing reputation as a hub for communication, and events advertisement and tracking. However, several recent research studies have shown that Twitter users (and microblogging platforms' users in general) are increasingly posting microblogs containing questions seeking answers from their readers. To help those users answer or route their questions, the problem of question identification in tweets has been studied over English tweets; up to our knowledge, no study has attempted it over Arabic (not to mention dialectal Arabic) tweets.

Twitter is currently one of the largest social hubs for users to spread and discuss news. For most of the top news stories happening, there are corresponding discussions on social media. In this demonstration TweetMogaz is presented, which is a platform for microblog search and filtering. It creates a real-time comprehensive report about what people discuss and share around news happening in certain regions. TweetMogaz reports the most popular tweets, jokes, videos, images, and news articles that people share about top news stories. Moreover, it allows users to search for specific topics. A scalable automatic technique for microblog filtering is used to obtain relevant tweets to a certain news category in a region. TweetMogaz.com demonstrates the effectiveness of our filtering technique for reporting public response toward news in different Arabic regions including Egypt and Syria in real-time.

The use of social media has profoundly affected social and political dynamics in the Arab world. In this paper, we explore the Arabic microblogs retrieval. We illustrate some of the challenges associated with Arabic microblog retrieval, which mainly stem from the use of different Arabic dialects that vary in lexical selection, morphology, and phonetics and lack orthographic and spelling conventions. We present some of the required processing for effective retrieval such as improved letter normalization, elongated word handling, stopword removal, and stemming

Searching social content in general and microblogs (aka tweets) in particular has been basic and limited, especially for time-sensitive topics. The currently implemented microblog search on sites such as Twitter is based on simple word matching and retrieves the most recent microblogs that match a given query. Furthermore, a user may obtain hundreds or perhaps thousands of microblogs in response to a given query, leading to information overload. We present a new multidimensional microblog search tool that generates a comprehensive report from microblogs instead of a flat list of recent/relevant microblogs for a given query. Reports may include tag-clouds, topic time series, and most popular and funny microblogs, etc. The tool can be configured for monitoring time-sensitive topics using a set of predefined queries. We demonstrate our system on Arabic and English microblog collections. Additionally, we show a special configuration of the system for monitoring the 2012 Egyptian presidential elections.

Queries in patent prior art search are full patent applications and much longer than standard ad hoc search and web search topics. Standard information retrieval (IR) techniques are not entirely effective for patent prior art search because of ambiguous terms in these massive queries. Reducing patent queries by extracting key terms has been shown to be ineffective mainly because it is not clear what the focus of the query is. An optimal query reduction algorithm must thus seek to retain the useful terms for retrieval favouring recall of relevant patents, but remove terms which impair IR effectiveness. We propose a new query reduction technique decomposing a patent application into constituent text segments and computing the Language Modeling (LM) similarities by calculating the probability of generating each segment from the top ranked documents. We reduce a patent query by removing the least similar segments from the query, hypothesising that removal of these segments can increase the precision of retrieval, while still retaining the useful context to achieve high recall. Experiments on the patent prior art search collection CLEF-IP 2010 show that the proposed method outperforms standard pseudo-relevance feedback (PRF) and a naive method of query reduction based on removal of unit frequency terms (UFTs).

Topics 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.

Decompounding has been found to improve information retrieval (IR) effectiveness in general domains for languages such as German or Dutch. We investigate if cross-language patent retrieval can profit from decompounding. This poses two challenges: i) There may be few resources such as parallel corpora available for training an machine translation system for a compounding language. ii) Patents have a specific writing style and vocabulary ("patentese"), which may affect the performance of decompounding and translation methods. Experiments on data from the CLEF-IP 2010 task show that decompounding patents for translation can overcome out-of-vocabulary problems (OOV) and that decompounding improves IR performance significantly for small training corpora.

Recent library digitization projects attempt to provide large collections of printed material from varying sources in a searchable format. The scanned documents are typically processed using Optical Character Recognition (OCR), which typically introduces errors in the text. This paper proposes a technique for correction of OCR degraded text that is independent of character-level OCR errors, and hence independent of scanned document source. It is based on language modeling in conjunction with a uniform character model that uses edit distance only. The technique compares well to state-of-the-art correction techniques that are based on language modeling and source-specific character error models. Although the proposed technique yielded lower correction effectiveness, its impact on retrieval effectiveness is statistically significant and at par with state-of-the-art correction techniques. The main requirement of the proposed technique is the training of a “good” language model matching genre, style, and temporal coverage. The advantage of being independent of character level errors is clear in applications were printed documents vary in source, font, and degradation level.

Information retrieval (IR) evaluation scores are generally designed to measure the effectiveness with which relevant documents are identified and retrieved. Many scores have been proposed for this purpose over the years. These have primarily focused on aspects of precision and recall, and while these are often discussed with equal importance, in practice most attention has been given to precision focused metrics. Even for recall-oriented IR tasks of growing importance, such as patent retrieval, these precision based scores remain the primary evaluation measures. Our study examines different evaluation measures for a recall-oriented patent retrieval task and demonstrates the limitations of the current scores in comparing different IR systems for this task. We introduce PRES, a novel evaluation metric for this type of application taking account of recall and the user's search effort. The behaviour of PRES is demonstrated on 48 runs from the CLEF-IP 2009 patent retrieval track. A full analysis of the performance of PRES shows its suitability for measuring the retrieval effectiveness of systems from a recall focused perspective taking into account the user's expected search effort.

Due to the existence of large numbers of legacy documents (such as old books and newspapers), improving retrieval effectiveness for OCR'ed documents continues to be an important problem. This article compares the effect of OCR error correction with and without language modeling and the effect of query garbling with weighted structured queries on the retrieval of OCR degraded Arabic documents. The results suggest that moderate error correction does not yield statistically significant improvement in retrieval effectiveness when indexing and searching using n-grams. Also, reversing error correction models to perform query garbling in conjunction with weighted structured queries yields improved retrieval effectiveness. Lastly, using very good error correction that utilizes language modeling yields the best improvement in retrieval effectiveness.