Barbara Poblete
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Barbara Poblete has a total of 51 co-authors. Here are the top co-authors by number of shared publications:
- Vanessa Murdock
Amazon
3 shared publications - Andrés Abeliuk
University of Chile
2 shared publications - Aidan Hogan
University of Chile
1 shared publication - Andrea Escobar
Millennium Inst Fdn Res Data, Santiago, Chile
1 shared publication Andres Abeliuk
University of Chile, Santiago, Chile National Center for Artificial Intelligence (CENIA), Santiago, Chile
1 shared publication- Andrés Cruz
Comparative Constitutions Project, University of Texas at Austin and the University of Chicago, Austin, TX, USA
1 shared publication
Latest Publications
- Open Access
- 16 October 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on the Web
- Vol. 19 (4) , 1-25
Large Language Models in Crisis Informatics for Zero and Few-Shot Classification
This article presents an exploration of the use of pre-trained Large Language Models (LLMs) for crisis classification to address labeled data dependency issues. We present a methodology that enhances open LLMs through fine-tuning, creating zero-shot and few-shot classifiers that approach traditional supervised models in classifying crisis-related messages. A comparative study evaluates crisis classification tasks using general domain pre-trained LLMs, crisis-specific LLMs, and traditional supervised learning methods, establishing a benchmark in the field. Our task-specific fine-tuned Llama model achieved a 69% macro F1 score in classifying humanitarian information–a remarkable 26% improvement compared to the Llama baseline, even with limited training data. Moreover, it outperformed ChatGPT4 by 3% in macro F1. This improvement increased to 71% macro F1 when fine-tuning Llama with multitask data. For the binary classification of messages as related vs. not related to crises, we observed that pre-trained LLMs, such as Llama 2 and ChatGPT4, performed well without fine-tuning, achieving an 87% macro F1 score with ChatGPT4. This research expands our knowledge of how to exploit the potential of LLMs for crisis classification, representing a great opportunity for crisis scenarios that lack labeled data. The findings emphasize the potential of LLMs in crisis informatics to address cold start challenges, especially critical in the initial phases of a disaster, while also showcasing their capacity to attain high accuracy even with limited training data.
- 16 October 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on the Web
- Vol. 19 (4) , 1-25
Open AccessLarge Language Models in Crisis Informatics for Zero and Few-Shot Classification
This article presents an exploration of the use of pre-trained Large Language Models (LLMs) for crisis classification to address labeled data dependency issues. We present a methodology that enhances open LLMs through fine-tuning, creating zero-shot and few-shot classifiers that approach traditional supervised models in classifying crisis-related messages. A comparative study evaluates crisis classification tasks using general domain pre-trained LLMs, crisis-specific LLMs, and traditional supervised learning methods, establishing a benchmark in the field. Our task-specific fine-tuned Llama model achieved a 69% macro F1 score in classifying humanitarian information–a remarkable 26% improvement compared to the Llama baseline, even with limited training data. Moreover, it outperformed ChatGPT4 by 3% in macro F1. This improvement increased to 71% macro F1 when fine-tuning Llama with multitask data. For the binary classification of messages as related vs. not related to crises, we observed that pre-trained LLMs, such as Llama 2 and ChatGPT4, performed well without fine-tuning, achieving an 87% macro F1 score with ChatGPT4. This research expands our knowledge of how to exploit the potential of LLMs for crisis classification, representing a great opportunity for crisis scenarios that lack labeled data. The findings emphasize the potential of LLMs in crisis informatics to address cold start challenges, especially critical in the initial phases of a disaster, while also showcasing their capacity to attain high accuracy even with limited training data.
- Open Access
- 16 June 2025
- Published by Radboud University in Information Retrieval Research
- Vol. 1 (1) , 1-2
Editorial
This editorial celebrates the first issue of the Information Retrieval Research Journal, IRRJ.
- 16 June 2025
- Published by Radboud University in Information Retrieval Research
- Vol. 1 (1) , 1-2
Open AccessEditorial
This editorial celebrates the first issue of the Information Retrieval Research Journal, IRRJ.
- Open Access
- 10 March 2025
- Published by Association for Computing Machinery (ACM)
- p. 1032-1035
A Shopping Agent for Addressing Subjective Product Needs
In e-commerce, customers often struggle to find relevant items when their needs involve subjective properties characterized by personal or collective perception, tastes, and opinions, which are typically not captured in catalog data. This challenge is particularly pronounced in event-based scenarios like gifting, where selecting the right product involves complex subjective reasoning. Customer reviews can be a valuable source of subjective information to bridge this gap. Consequently, customers often spend significant amount of time navigating multiple products and reading numerous reviews to find suitable gifts that meet their needs. In order to reduce the effort involved, we propose an agentic approach driven by large language models to streamline this process by autonomously executing various user actions. These include computational tasks like vagueness detection and subjective product needs extraction, conversational interactions to gather missing user information, and web browsing actions that search for product details, reviews, and review images. Additionally, the agent employs generative actions to synthesize gifting ideas and explanations, helping users discover suitable products more efficiently. The proposed approach not only reduces the cognitive burden on users but also facilitates the exploration of a wider range of products. Our solution highlights the potential of autonomous agents to handle subjective queries in e-commerce, enhancing personalization, product exploration, and selection in a user-centric manner.
- 10 March 2025
- Published by Association for Computing Machinery (ACM)
- p. 1032-1035
Open AccessA Shopping Agent for Addressing Subjective Product Needs
In e-commerce, customers often struggle to find relevant items when their needs involve subjective properties characterized by personal or collective perception, tastes, and opinions, which are typically not captured in catalog data. This challenge is particularly pronounced in event-based scenarios like gifting, where selecting the right product involves complex subjective reasoning. Customer reviews can be a valuable source of subjective information to bridge this gap. Consequently, customers often spend significant amount of time navigating multiple products and reading numerous reviews to find suitable gifts that meet their needs. In order to reduce the effort involved, we propose an agentic approach driven by large language models to streamline this process by autonomously executing various user actions. These include computational tasks like vagueness detection and subjective product needs extraction, conversational interactions to gather missing user information, and web browsing actions that search for product details, reviews, and review images. Additionally, the agent employs generative actions to synthesize gifting ideas and explanations, helping users discover suitable products more efficiently. The proposed approach not only reduces the cognitive burden on users but also facilitates the exploration of a wider range of products. Our solution highlights the potential of autonomous agents to handle subjective queries in e-commerce, enhancing personalization, product exploration, and selection in a user-centric manner.
- Open Access
- 3 June 2024
- Published by Association for Computing Machinery (ACM)
- p. 947-957
Gender Representation Across Online Retail Products
We present a broad characterization of gender representation in a large heterogeneous sample of retail products. In particular, we study online product textual information, such as titles and descriptions. Our goal is to understand from a semantic perspective, differences and similarities in how girls (women) and boys (men) are represented. We perform a comparative analysis of the language used in gendered products (i.e., products that mention exclusively either of these two genders), and additionally compare it to products that are explicitly gender neutral or inclusive. We found that the adjectives, skills, occupations, and values described in gendered products tended to reinforce stereotypes. Some of these stereotypes are aligned with historical findings from research on traditional off-line retail stores, and others are new owing to the up-to-date product dataset our research is based on. By leveraging additional existing resources we were able to gain insight into how certain product descriptions reflect stereotypes that are related to soft-skills and hierarchical occupational information. Conversely, we found that a large segment of products present explicitly as gender neutral or inclusive. We explore whether the language used by gender-inclusive products can be useful to improve stereotypes reflected in gendered product text. Specifically, we study its effect in word embedding fairness through debiasing techniques.
- 3 June 2024
- Published by Association for Computing Machinery (ACM)
- p. 947-957
Open AccessGender Representation Across Online Retail Products
We present a broad characterization of gender representation in a large heterogeneous sample of retail products. In particular, we study online product textual information, such as titles and descriptions. Our goal is to understand from a semantic perspective, differences and similarities in how girls (women) and boys (men) are represented. We perform a comparative analysis of the language used in gendered products (i.e., products that mention exclusively either of these two genders), and additionally compare it to products that are explicitly gender neutral or inclusive. We found that the adjectives, skills, occupations, and values described in gendered products tended to reinforce stereotypes. Some of these stereotypes are aligned with historical findings from research on traditional off-line retail stores, and others are new owing to the up-to-date product dataset our research is based on. By leveraging additional existing resources we were able to gain insight into how certain product descriptions reflect stereotypes that are related to soft-skills and hierarchical occupational information. Conversely, we found that a large segment of products present explicitly as gender neutral or inclusive. We explore whether the language used by gender-inclusive products can be useful to improve stereotypes reflected in gendered product text. Specifically, we study its effect in word embedding fairness through debiasing techniques.
- Open Access
- 21 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 1400-1410
Bias Invariant Approaches for Improving Word Embedding Fairness
Many public pre-trained word embeddings have been shown to encode different types of biases. Embeddings are often obtained from training on large pre-existing corpora, and therefore resulting biases can be a reflection of unfair representations in the original data. Bias, in this scenario, is a challenging problem since current mitigation techniques require knowing and understanding existing biases in the embedding, which is not always possible. In this work, we propose to improve word embedding fairness by borrowing methods from the field of data privacy. The idea behind this approach is to treat bias as if it were a special type of training data leakage. This has the unique advantage of not requiring prior knowledge of potential biases in word embeddings. We investigated two types of privacy algorithms, and measured their effect on bias using four different metrics. To investigate techniques from differential privacy, we applied Gaussian perturbation to public pre-trained word embeddings. To investigate noiseless privacy, we applied vector quantization during training. Experiments show that both approaches improve fairness for commonly used embeddings, and additionally, noiseless privacy techniques reduce the size of the resulting embedding representation.
- 21 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 1400-1410
Open AccessBias Invariant Approaches for Improving Word Embedding Fairness
Many public pre-trained word embeddings have been shown to encode different types of biases. Embeddings are often obtained from training on large pre-existing corpora, and therefore resulting biases can be a reflection of unfair representations in the original data. Bias, in this scenario, is a challenging problem since current mitigation techniques require knowing and understanding existing biases in the embedding, which is not always possible. In this work, we propose to improve word embedding fairness by borrowing methods from the field of data privacy. The idea behind this approach is to treat bias as if it were a special type of training data leakage. This has the unique advantage of not requiring prior knowledge of potential biases in word embeddings. We investigated two types of privacy algorithms, and measured their effect on bias using four different metrics. To investigate techniques from differential privacy, we applied Gaussian perturbation to public pre-trained word embeddings. To investigate noiseless privacy, we applied vector quantization during training. Experiments show that both approaches improve fairness for commonly used embeddings, and additionally, noiseless privacy techniques reduce the size of the resulting embedding representation.
- Open Access
- 2 June 2023
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the International AAAI Conference on Web and Social Media
- Vol. 17, 754-765
Cross-Lingual and Cross-Domain Crisis Classification for Low-Resource Scenarios
Social media data has emerged as a useful source of timely information about real-world crisis events. One of the main tasks related to the use of social media for disaster management is the automatic identification of crisis-related messages. Most of the studies on this topic have focused on the analysis of data for a particular type of event in a specific language. This limits the possibility of generalizing existing approaches because models cannot be directly applied to new types of events or other languages. In this work, we study the task of automatically classifying messages that are related to crisis events by leveraging cross-language and cross-domain labeled data. Our goal is to make use of labeled data from high-resource languages to classify messages from other (low-resource) languages and/or of new (previously unseen) types of crisis situations. For our study we consolidated from the literature a large unified dataset containing multiple crisis events and languages. Our empirical findings show that it is indeed possible to leverage data from crisis events in English to classify the same type of event in other languages, such as Spanish and Italian (80.0% F1-score). Furthermore, we achieve good performance for the cross-domain task (80.0% F1-score) in a cross-lingual setting. Overall, our work contributes to improving the data scarcity problem that is so important for multilingual crisis classification. In particular, mitigating cold-start situations in emergency events, when time is of essence.
- 2 June 2023
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the International AAAI Conference on Web and Social Media
- Vol. 17, 754-765
Open AccessCross-Lingual and Cross-Domain Crisis Classification for Low-Resource Scenarios
Social media data has emerged as a useful source of timely information about real-world crisis events. One of the main tasks related to the use of social media for disaster management is the automatic identification of crisis-related messages. Most of the studies on this topic have focused on the analysis of data for a particular type of event in a specific language. This limits the possibility of generalizing existing approaches because models cannot be directly applied to new types of events or other languages. In this work, we study the task of automatically classifying messages that are related to crisis events by leveraging cross-language and cross-domain labeled data. Our goal is to make use of labeled data from high-resource languages to classify messages from other (low-resource) languages and/or of new (previously unseen) types of crisis situations. For our study we consolidated from the literature a large unified dataset containing multiple crisis events and languages. Our empirical findings show that it is indeed possible to leverage data from crisis events in English to classify the same type of event in other languages, such as Spanish and Italian (80.0% F1-score). Furthermore, we achieve good performance for the cross-domain task (80.0% F1-score) in a cross-lingual setting. Overall, our work contributes to improving the data scarcity problem that is so important for multilingual crisis classification. In particular, mitigating cold-start situations in emergency events, when time is of essence.
- Open Access
- 2 June 2023
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the International AAAI Conference on Web and Social Media
- Vol. 17, 808-819
Characterizing and Identifying Socially Shared Self-Descriptions in Product Reviews
Online e-commerce product reviews can be highly influential in a customer's decision-making processes. Reviews often describe personal experiences with a product and provide candid opinions about a product's pros and cons. In some cases, reviewers choose to share information about themselves, just as they might do in social platforms. These descriptions are a valuable source of information about who finds a product most helpful. Customers benefit from key insights about a product from people with their same interests and sellers might use the information to better serve their customers needs. In this work, we present a comprehensive look into voluntary self-descriptive information found in public customer reviews. We analyzed what people share about themselves and how this contributes to their product opinions. We developed a taxonomy of types of self-descriptions, and a machine-learned classification model of reviews according to this taxonomy. We present new quantitative findings, and a thematic study of the perceived purpose descriptions in reviews.
- 2 June 2023
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the International AAAI Conference on Web and Social Media
- Vol. 17, 808-819
Open AccessCharacterizing and Identifying Socially Shared Self-Descriptions in Product Reviews
Online e-commerce product reviews can be highly influential in a customer's decision-making processes. Reviews often describe personal experiences with a product and provide candid opinions about a product's pros and cons. In some cases, reviewers choose to share information about themselves, just as they might do in social platforms. These descriptions are a valuable source of information about who finds a product most helpful. Customers benefit from key insights about a product from people with their same interests and sellers might use the information to better serve their customers needs. In this work, we present a comprehensive look into voluntary self-descriptive information found in public customer reviews. We analyzed what people share about themselves and how this contributes to their product opinions. We developed a taxonomy of types of self-descriptions, and a machine-learned classification model of reviews according to this taxonomy. We present new quantitative findings, and a thematic study of the perceived purpose descriptions in reviews.
- Open Access
- 30 April 2023
- Published by Association for Computing Machinery (ACM)
- p. 1
Using diversity as a source of scientific innovation for the Web
The Web has become a resource that allows us to make sense of social phenomena around the world. This started the moment users became content creators, and has grown with the emergence of social platforms tailored to our need to connect and share with others. Throughout my work, I’ve come to appreciate how social media has democratized access to real-world news and social sentiment, while also witnessing the loss of trust created by fake information. As a computer scientist from Chile in Latin America, I have worked on a range of problems that were driven by local needs. Many times, I have tried to apply state of the art solutions to well-known problems, only to find that these don’t work outside of their initial evaluation dataset. In this talk, I’ll discuss how geographical, language, and social diversity have opened new avenues for innovation and better understanding the social Web. I’ll also show that to truly create useful technological solutions, we must develop inclusive research and resources.
- 30 April 2023
- Published by Association for Computing Machinery (ACM)
- p. 1
Open AccessUsing diversity as a source of scientific innovation for the Web
The Web has become a resource that allows us to make sense of social phenomena around the world. This started the moment users became content creators, and has grown with the emergence of social platforms tailored to our need to connect and share with others. Throughout my work, I’ve come to appreciate how social media has democratized access to real-world news and social sentiment, while also witnessing the loss of trust created by fake information. As a computer scientist from Chile in Latin America, I have worked on a range of problems that were driven by local needs. Many times, I have tried to apply state of the art solutions to well-known problems, only to find that these don’t work outside of their initial evaluation dataset. In this talk, I’ll discuss how geographical, language, and social diversity have opened new avenues for innovation and better understanding the social Web. I’ll also show that to truly create useful technological solutions, we must develop inclusive research and resources.
- Open Access
Cross-Lingual and Cross-Domain Crisis Classification for Low-Resource Scenarios
Social media data has emerged as a useful source of timely information about real-world crisis events. One of the main tasks related to the use of social media for disaster management is the automatic identification of crisis-related messages. Most of the studies on this topic have focused on the analysis of data for a particular type of event in a specific language. This limits the possibility of generalizing existing approaches because models cannot be directly applied to new types of events or other languages. In this work, we study the task of automatically classifying messages that are related to crisis events by leveraging cross-language and cross-domain labeled data. Our goal is to make use of labeled data from high-resource languages to classify messages from other (low-resource) languages and/or of new (previously unseen) types of crisis situations. For our study we consolidated from the literature a large unified dataset containing multiple crisis events and languages. Our empirical findings show that it is indeed possible to leverage data from crisis events in English to classify the same type of event in other languages, such as Spanish and Italian (80.0% F1-score). Furthermore, we achieve good performance for the cross-domain task (80.0% F1-score) in a cross-lingual setting. Overall, our work contributes to improving the data scarcity problem that is so important for multilingual crisis classification. In particular, mitigating cold-start situations in emergency events, when time is of essence.
Open AccessCross-Lingual and Cross-Domain Crisis Classification for Low-Resource Scenarios
Social media data has emerged as a useful source of timely information about real-world crisis events. One of the main tasks related to the use of social media for disaster management is the automatic identification of crisis-related messages. Most of the studies on this topic have focused on the analysis of data for a particular type of event in a specific language. This limits the possibility of generalizing existing approaches because models cannot be directly applied to new types of events or other languages. In this work, we study the task of automatically classifying messages that are related to crisis events by leveraging cross-language and cross-domain labeled data. Our goal is to make use of labeled data from high-resource languages to classify messages from other (low-resource) languages and/or of new (previously unseen) types of crisis situations. For our study we consolidated from the literature a large unified dataset containing multiple crisis events and languages. Our empirical findings show that it is indeed possible to leverage data from crisis events in English to classify the same type of event in other languages, such as Spanish and Italian (80.0% F1-score). Furthermore, we achieve good performance for the cross-domain task (80.0% F1-score) in a cross-lingual setting. Overall, our work contributes to improving the data scarcity problem that is so important for multilingual crisis classification. In particular, mitigating cold-start situations in emergency events, when time is of essence.
- Open Access
- 18 February 2022
- Published by MDPI AG in ISPRS International Journal of Geo-Information
- Vol. 11 (2) , 147
Language Modeling on Location-Based Social Networks
The popularity of mobile devices with GPS capabilities, along with the worldwide adoption of social media, have created a rich source of text data combined with spatio-temporal information. Text data collected from location-based social networks can be used to gain space–time insights into human behavior and provide a view of time and space from the social media lens. From a data modeling perspective, text, time, and space have different scales and representation approaches; hence, it is not trivial to jointly represent them in a unified model. Existing approaches do not capture the sequential structure present in texts or the patterns that drive how text is generated considering the spatio-temporal context at different levels of granularity. In this work, we present a neural language model architecture that allows us to represent time and space as context for text generation at different granularities. We define the task of modeling text, timestamps, and geo-coordinates as a spatio-temporal conditioned language model task. This task definition allows us to employ the same evaluation methodology used in language modeling, which is a traditional natural language processing task that considers the sequential structure of texts. We conduct experiments over two datasets collected from location-based social networks, Twitter and Foursquare. Our experimental results show that each dataset has particular patterns for language generation under spatio-temporal conditions at different granularities. In addition, we present qualitative analyses to show how the proposed model can be used to characterize urban places.
- 18 February 2022
- Published by MDPI AG in ISPRS International Journal of Geo-Information
- Vol. 11 (2) , 147
Open AccessLanguage Modeling on Location-Based Social Networks
The popularity of mobile devices with GPS capabilities, along with the worldwide adoption of social media, have created a rich source of text data combined with spatio-temporal information. Text data collected from location-based social networks can be used to gain space–time insights into human behavior and provide a view of time and space from the social media lens. From a data modeling perspective, text, time, and space have different scales and representation approaches; hence, it is not trivial to jointly represent them in a unified model. Existing approaches do not capture the sequential structure present in texts or the patterns that drive how text is generated considering the spatio-temporal context at different levels of granularity. In this work, we present a neural language model architecture that allows us to represent time and space as context for text generation at different granularities. We define the task of modeling text, timestamps, and geo-coordinates as a spatio-temporal conditioned language model task. This task definition allows us to employ the same evaluation methodology used in language modeling, which is a traditional natural language processing task that considers the sequential structure of texts. We conduct experiments over two datasets collected from location-based social networks, Twitter and Foursquare. Our experimental results show that each dataset has particular patterns for language generation under spatio-temporal conditions at different granularities. In addition, we present qualitative analyses to show how the proposed model can be used to characterize urban places.