A location-based news article recommendation with explicit localized semantic analysis

In this era of fake news and political polarization, it is desirable to have a system to enable users to access balanced news content. Current solutions focus on top down, server based approaches to decide whether a news article is fake or biased, and display only trusted news to the end users. In this paper, we follow a different approach to help the users make informed choices about which news they want to read, making users aware in real time of the bias in news articles they were browsing and recommending news articles from other sources on the same topic with different levels of bias. We use a recent Pew research report to collect news sources that readers with varying political inclinations prefer to read. We then scrape news articles on a variety of topics from these varied news sources. After this, we perform clustering to find similar topics of the articles, as well as calculate a bias score for each article. For a news article the user is currently reading, we display the bias score and also display other articles on the same topic, out of the previously collected articles, from different news sources. This we present to the user. This approach, we hope, would make it possible for users to access more balanced articles on given news topics. We present the implementation details of the system along with some preliminary results on news articles.

Online news article reading has become very popular as the World Wide Web provides an access to variety of news articles from large volume of sources around the world. A key challenge of news portals is to provide articles to the users based on their interest. Personalized news recommendation systems provide news articles to the readers based on their interest rather than presenting articles in order of their occurrences. The effectiveness of news recommendation systems reduces due to lack of user ratings and automated novelty detection. A progressive summary helps a user to monitor changes in news items over a period of time. The automatic detection of novelty in personalized news recommendation system could improve a reader's search experience by providing news items that add more information's to already known information's to the users. This paper presents a rough set based collaborative filtering approach to predict a missing news category rating values of a user, and a new novelty detection approach to improve ranking of novel news items. The proposed approach maximizes the accuracy of the news article recommendation to the user according to their interest. Experimental results show the efficiency of the proposed approach.

With the increasing interest in location-based services, location comparison gains more and more attentions. One of the best ways to represent a location is to use topics that are generated near the location. In order to compare locations through such geographical topics, two conditions need to be met. One is that the topic set should be fixed but cover various aspects of all possible locations, and the other is that geographical topics often depend on each other. This paper proposes Probabilistic Explicit Semantic Analysis (PESA) that meets these conditions. PESA represents a location as a weighted topic vector where each topic is a Wikipedia concept. The number of Wikipedia concepts is fixed, but their enormous quantity allows PESA to be used to compare various locations. In addition, link information within Wikipedia articles is used to compute prior probabilities of topics considering their dependencies. That is, it enables PESA to model the topic dependency. PESA was evaluated using eighteen locations in three distinct geographical categories and compare it with LDA and ESA. The experimental results that PESA outperformed LDA and ESA highlighting its superiority in location comparison.

Protected areas for conservation and poverty alleviation: experiences from Madagascar Charlie J. Gardner*, Martin E. Nicoll, Tsibara Mbohoahy, Kirsten L. L. Oleson, Anitry N. Ratsifandrihamanana, Joelisoa Ratsirarson, Lily-Arison Ren e de Roland, Malika Virah-Sawmy, Bienvenue Zafindrasilivonona and Zoe G. Davies WWF Madagascar and Western Indian Ocean Programme Office, BP738, Antananarivo 101, Madagascar; Durrell Institute of Conservation and Ecology (DICE), School of Anthropology and Conservation, University of Kent, Canterbury, Kent CT2 7NR, UK; D epartement de Biologie, Facult e des Sciences, Universit e de Toliara, Toliara 601, BP 185, Toliara, Madagascar; Blue Ventures Conservation, Level 2 Annex, Omnibus Business Centre, 39-41 North Road, N7 9DP London, UK; ESSA-D epartement Eaux et Forets, Universit e d’Antananarivo, BP 175 Antananarivo, Madagascar; and The Peregrine Fund, BP 4113 Antananarivo, Madagascar

Reducing explicit semantic representation vectors using Latent Dirichlet Allocation

Since its debut the Explicit Semantic Analysis (ESA) has received much attention in the IR community. ESA has been proven to perform surprisingly well in several tasks and in different contexts. However, given the conceptual motivation for ESA, recent work has observed unexpected behavior. In this paper we look at the foundations of ESA from a theoretical point of view and employ a general probabilistic model for term weights which reveals how ESA actually works. Based on this model we explain some of the phenomena that have been observed in previous work and support our findings with new experiments. Moreover, we provide a theoretical grounding on how the size and the composition of the index collection affect the ESA-based computation of similarity values for texts.

최근 스마트 기기 사용자의 효율적인 일정 관리를 위해 다양한 일정 관리 에이전트들이 연구되고 있지만 아직까지는 일정을 기록하거나 확인해주는 수준에 머물고 있다. 사용자의 일정을 효율적으로 관리하기 위해서는 계획한 일정의 수행 여부 등을 모니터링하여 사용자에게 일정을 제대로 수행할 수 있도록 도움을 주거나, 새로운 일정 수립 시 사용자의 일정 수립 패턴에 적합하게 일정을 계획할 수 있도록 피드백 해 줄 수 있어야 한다. 본 논문에서는 사용자가 일정을 수행하거나 새로운 일정을 계획할 때, 획득된 사용자 컨텍스트를 이용하여 사용자의 행동을 추론하고 사용자의 행동 패턴에 따른 일정 관련 피드백을 제공하는 일정 관리 에이전트를 제안한다. 본 에이전트에서는 수집된 사용자 컨텍스트 정보를 전처리 후 베이지안 네트워크에 적용하여 사용자의 행동을 추론한다. 또한 사용자 일정 수행 여부의 확인 및 새로운 일정 수립에 필요한 피드백을 제공하기 위해 사용자 일정과 위치 및 시간 컨텍스트에 대하여 컨텍스트 트리 패턴 매칭 기법을 적용하였으며, 모바일 환경에서 6주간의 사용자 시뮬레이션을 통해 검증하였다. Recently, diverse schedule management agents are being researched for the efficient schedule management of smart devices users, but they remain at a confirmatory level. In order to efficiently manage user's schedules, execution of planned schedules should be monitored to help users properly execute their schedules, or feedback must be given so that when setting up new schedules, users can plan their schedule according to their schedule establishment patterns. This research proposes a schedule management agent that infers the user's behaviors by using acquired user context, and provides schedule related feedback depending on the user's behavior patterns, when users are executing their schedules or planning new schedules. For this, collected user context information is preprocessed and user's behavior is inferred by Bayesian network. Also, in order to provide feedbacks necessary for confirming the user's schedule execution and new schedule establishment, a context tree pattern matching method for the user's schedule, location and time contexts was applied, then verified with 6 weeks of user simulation in a mobile environment.

Recent sequential recommendation models rely increasingly on consecutive short-term user-item interaction sequences to model user interests. These approaches have, however, raised concerns about both short- and long-term interests. (1) short-term: interaction sequences may not result from a monolithic interest, but rather from several intertwined interests, even within a short period of time, resulting in their failures to model skip behaviors; (2) long-term: interaction sequences are primarily observed sparsely at discrete intervals, other than consecutively over the long run. This renders difficulty in inferring long-term interests, since only discrete interest representations can be derived, without taking into account interest dynamics across sequences. In this study, we address these concerns by learning (1) multi-scale representations of short-term interests; and (2) dynamics-aware representations of long-term interests. To this end, we present an Interest Dynamics modeling framework using generative Neural Processes, coined IDNP, to model user interests from a functional perspective. IDNP learns a global interest function family to define each user's long-term interest as a function instantiation, manifesting interest dynamics through function continuity. Specifically, IDNP first encodes each user's short-term interactions into multi-scale representations, which are then summarized as user context. By combining latent global interest with user context, IDNP then reconstructs long-term user interest functions and predicts interactions at upcoming query timestep. Moreover, IDNP can model such interest functions even when interaction sequences are limited and non-consecutive. Extensive experiments on four real-world datasets demonstrate that our model outperforms the state-of-the-art on various evaluation metrics.

Recent years have witnessed the tremendous development of social media, which attracts a vast number of Internet users. The high-dimension content generated by these users provides an unique opportunity to understand their behavior deeply. As one of the most fundamental topics, location estimation attracts more and more research efforts. Different from the previous literature, we find that user's location is strongly related to user interest. Based on this, we first build a detection model to mine user interest from short text. We then establish the mapping between location function and user interest before presenting an efficient framework to predict the user's location with convincing fidelity. Thorough evaluations and comparisons on an authentic data set show that our proposed model significantly outperforms the state-of-the-arts approaches. Moreover, the high efficiency of our model also guarantees its applicability in real-world scenarios.

In this demo we present a robust system for delivering real-time news recommendation to the user based on the user's history of the past visits to the site, current user's context and popularity of stories. Our system is running live providing real-time recommendations of news articles. The system handles overspecializing as we recommend categories as opposed to items, it implicitly uses collaboration by taking into account user context and popular items and, it can handle new users by using context information. A unique characteristic of our system is that it prefers freshness over relevance, which is important for recommending news articles in real-world setting as addressed here. We experimentally compare the proposed approach as implemented in our system against several state-of-the-art alternatives and show that it significantly outperforms them.

AI alignment describes the challenge of ensuring (future) AI systems behave in accordance with societal norms, values, and goals. Alignment is now central to research on foundation models and AI agents. Most recent work focuses on methods to prevent potentially harmful biases, account for social inequalities, improve AI safety, and enhance explainability. Notably, the debiasing 'corrections' applied to various stages of AI/ML workflows may lead to outcomes that diverge strongly from current statistical realities on the ground. For instance, text-to-image models may depict a balanced gender ratio of company leadership, despite existing imbalances. However, an often overlooked dimension is the geographic variability of alignment. What is considered appropriate, truthful, or legal can vary greatly between regions due to cultural differences, political realities, or legislation. Hence, some model outputs align without further knowledge of the user's geospatial context, while others are highly sensitive to it. Put differently, whether these outputs align varies geographically. E.g., statements about Kashmir cannot be generated without understanding the user's origin and current location. From a common-sense perspective, this problem is hardly new. In fact, Google Maps will render different administrative borders based on the user's location. Interestingly, in both knowledge representation and representation learning, spatiotemporal context, e.g., due to the monotonic nature of reasoning, remains a major challenge. Until very recently, these were largely theoretical problems. What is truly novel is the scale and level of automation at which AI systems now mediate knowledge, express opinions, and represent reality to millions of users across borders, often with little transparency or oversight regarding how context is handled. With agentic AI on the horizon, the urgency for pluralistic, geographically aware alignment, rather than one-size-fits-all solutions, is growing. Here, we motivate and formalize the vision of geo-alignment, outline how it goes beyond pluralistic alignment by offering learnable spatially explicit patterns, and suggest concrete avenues for future research.

The relevance of the multi-armed bandit problem has risen in the past few years with the need for online optimization techniques in Internet systems, such as online advertisement and news article recommendation. At the same time, these applications reveal that state-of-the-art solution schemes do not scale well with the number of bandit arms. In this paper, we present two types of Successive Reduction (SR) strategies - 1) Successive Reduction Hoeffding (SRH) and 2) Successive Reduction Order Statistics (SRO). Both use an Order Statistics based Thompson Sampling method for arm selection, and then successively eliminate bandit arms from consideration based on a confidence threshold. While SRH uses Hoeffding Bounds for elimination, SRO uses the probability of an arm being superior to the currently selected arm to measure confidence. A computationally efficient scheme for pairwise calculation of the latter probability is also presented in this paper. Using SR strategies, sampling resources and arm pulls are not wasted on arms that are unlikely to be the optimal one. To demonstrate the scalability of our proposed schemes, we compare them with two state-of-the-art approaches, namely pure Thompson Sampling and UCB-Tuned. The empirical results are truly conclusive, with the performance advantage of proposed SRO scheme increasing persistently with the number of bandit arms while the SRH scheme shows similar performance as pure Thompson Sampling. We thus believe that SR algorithms will open up for improved performance in Internet based on-line optimization, and tackling of larger problems.

SRL-ESA-TextSum: A text summarization approach based on semantic role labeling and explicit semantic analysis

Recently, exploiting a knowledge graph (KG) to enrich the semantic representation of a news article have been proven to be effective for news recommendation. These solutions focus on the representation learning for news articles with additional information in the knowledge graph, where the user representations are mainly derived based on these news representations later. However, different users would hold different interests on the same news article. In other words, directly identifying the entities relevant to the user's interest and deriving the resultant user representation could enable a better news recommendation and explanation.

This paper presents "ConServ", a Web service for context management. ConServ allows smart spaces to access user's context data according to user-defined policies. This Web service addresses the sharing and management of context data between smart spaces and as a result facilitates the creation of new smart spaces and the enhancement of old ones. Data related to a user's location, calendar, habits, relationships and privacy policy are combined to provide rich context data while users are provided with a single place where they can control the access of all smart spaces to their context data. ConServ provides a set of ontologies, which leverage existing popular ontologies, to model user's context data and the interacting smart spaces.