This paper introduces deep learning methods for high-resolution (30-meter) land surface temperature (LST) forecasting, addressing a critical gap in climate science and urban planning. We propose novel architectures, including DeepSatNet, which combines transfer learning from pre-trained networks with attention mechanisms. By fusing Landsat imagery and meteorological data, our models achieve significant improvements over baseline methods, with DeepSatNet demonstrating a 85.7% reduction in Root Mean Square Error compared to a persistence baseline. Our approach outperforms theoretical best-case scenarios for lower-resolution models, such as GraphCast, highlighting the importance of high-resolution modeling for accurate LST prediction. The models’ effectiveness across diverse environments suggests strong generalization capabilities, opening new avenues for urban heat management, energy grid optimization, and climate adaptation strategies. This research demonstrates that high-resolution LST forecasting is both achievable and essential for addressing urgent climate challenges

In this paper, we revisit the problem of influence maximization with fairness, which aims to select k influential nodes to maximise the spread of information in a network, while ensuring that selected sensitive user attributes (e.g., gender, location, origin, race, etc.) are fairly affected, i.e., are proportionally similar between the original network and the affected users. Recent studies on this problem focused only on extremely small networks, hence the challenge remains on how to achieve a scalable solution, applicable to networks with millions or billions of nodes. We propose an approach that is based on learning node representations (embeddings) for fair spread from diffusion cascades, instead of the social connectivity, and in this way we can deal with very large graphs. We propose two data-driven approaches: (a) fairness-based participant sampling (FPS), and (b) fairness as context (FAC). Spread related user features, such as the probability of diffusing information to others, are derived from the historical information cascades, using a deep neural network. The extracted features are then used in selecting influencers that maximize the influence spread, while being also fair with respect to the chosen sensitive attributes. In FPS, fairness and cascade length information are considered independently in the decision-making process, while FAC considers these information facets jointly and takes into account correlations between them. The proposed algorithms are generic and represent the first policy-driven solutions that can be applied to arbitrary sets of sensitive attributes at scale. We evaluate the performance of our solutions on a real-world public dataset (Sina Weibo) and on a hybrid real-synthetic dataset (Digg), which exhibit all the facets that we exploit, namely diffusion network, diffusion traces, and user profiles. These experiments show that our methods outperform the state-the-art solutions in terms of spread, fairness, and scalability.

An important metric of users' satisfaction and engagement within on-line streaming services is the user session length, i.e. the amount of time they spend on a service continuously without interruption. Being able to predict this value directly benefits the recommendation and ad pacing contexts in music and video streaming services. Recent research has shown that predicting the exact amount of time spent is highly nontrivial due to many external factors for which a user can end a session, and the lack of predictive covariates. Most of the other related literature on duration based user engagement has focused on dwell time for websites, for search and display ads, mainly for post-click satisfaction prediction or ad ranking. In this work we present a novel framework inspired by hierarchical Bayesian modeling to predict, at the moment of login, the amount of time a user will spend in the streaming service. The time spent by a user on a platform depends upon user-specific latent variables which are learned via hierarchical shrinkage. Our framework enjoys theoretical guarantees and naturally incorporates flexible parametric/nonparametric models on the covariates, including models robust to outliers. Our proposal is found to outperform state-of-the-art estimators in terms of efficiency and predictive performance on real world public and private datasets.

Online audio advertising is a particular form of advertising used abundantly in online music streaming services. In these platforms, which tend to host tens of thousands of unique audio advertisements (ads), providing high quality ads ensures a better user experience and results in longer user engagement. Therefore, the automatic assessment of these ads is an important step toward audio ads ranking and better audio ads creation.

Session length is a very important aspect in determining a user's satisfaction with a media streaming service. Being able to predict how long a session will last can be of great use for various downstream tasks, such as recommendations and ad scheduling. Most of the related literature on user interaction duration has focused on dwell time for websites, usually in the context of approximating post-click satisfaction either in search results, or display ads.

Modern search applications feature real-time as-you-type query search. In its elementary form, the problem consists in retrieving a set of k search results, that is, performing a search with a given prefix, and showing the top-ranked results. In this article, we focus on as-you-type keyword search over social media, that is, data published by users who are interconnected through a social network. We adopt a “network-aware” interpretation for information relevance, by which information produced by users who are closer to the user issuing a request is considered more relevant. This query model raises new challenges for effectiveness and efficiency in online search, even when the intent of the user is fully specified, as a complete query given as input in one keystroke. This is mainly because it requires a joint exploration of the social space and traditional IR indexes, such as inverted lists. We describe a memory-efficient and incremental prefix-based retrieval algorithm, which also exhibits an anytime behavior, allowing output of the most likely answer within any chosen runtime limit. We evaluate our approach through extensive experiments for several applications and search scenarios. We consider searching for posts in microblogging (Twitter and Tumblr), for businesses (Yelp), as well as for movies (Amazon) based on reviews. We also conduct a series of experiments comparing our algorithm with baselines using state-of-the-art techniques and measuring the improvements brought by several key optimizations. They show that our solution is effective in answering real-time as-you-type searches over social media.

We present in this paper a novel approach for as-you-type top-k keyword search over social media. We adopt a natural "network-aware" interpretation for information relevance, by which information produced by users who are closer to the seeker is considered more relevant. In practice, this query model poses new challenges for effectiveness and efficiency in online search, even when a complete query is given as input in one keystroke. This is mainly because it requires a joint exploration of the social space and classic IR indexes such as inverted lists. We describe a memory-efficient and incremental prefix-based retrieval algorithm, which also exhibits an anytime behavior, allowing to output the most likely answer within any chosen running-time limit. We evaluate it through extensive experiments for several applications and search scenarios, including searching for posts in micro-blogging (Twitter and Tumblr), as well as searching for businesses based on reviews in Yelp. They show that our solution is effective in answering real-time as-you-type searches over social media.

Users may strive to formulate an adequate textual query for their information need. Search engines assist the users by presenting query suggestions. To preserve the original search intent, suggestions should be context-aware and account for the previous queries issued by the user. Achieving context awareness is challenging due to data sparsity. We present a novel hierarchical recurrent encoder-decoder architecture that makes possible to account for sequences of previous queries of arbitrary lengths. As a result, our suggestions are sensitive to the order of queries in the context while avoiding data sparsity. Additionally, our model can suggest for rare, or long-tail, queries. The produced suggestions are synthetic and are sampled one word at a time, using computationally cheap decoding techniques. This is in contrast to current synthetic suggestion models relying upon machine learning pipelines and hand-engineered feature sets. Results show that our model outperforms existing context-aware approaches in a next query prediction setting. In addition to query suggestion, our architecture is general enough to be used in a variety of other applications.

Recommender systems used in current online social platforms make recommendations by only considering how relevant an item is to a specific user but they ignore the fact that, thanks to mechanisms like sharing or re-posting across the underlying social network, an item recommended to a user i propagates through the network and can reach another user j without needing to be explicitly recommended to j too. Overlooking this fact may lead to an inefficient use of the limited recommendation slots. These slots can instead be exploited more profitably by avoiding unnecessary duplicates and recommending other equally relevant items.

Topic discovery and evolution (TDE) has been a problem which has gained long standing interest in the research community. The goal in topic discovery is to identify groups of keywords from large corpora so that the information in those corpora are summarized succinctly. The nature of text corpora has changed dramatically in the past few years with the advent of social media. Social media services allow users to constantly share, follow and comment on posts from other users. Hence, such services have given a new dimension to the traditional text corpus. The new dimension being that today's corpora have a social context embedded in them in terms of the community of users interested in a particular post, their profiles etc. We wish to harness this social context that comes along with the textual content for TDE. In particular, our goal is to both qualitatively and quantitatively analyze when social context actually helps with TDE. Methodologically, we approach the problem of TDE by a proposing non-negative matrix factorization (NMF) based model that incorporates both the textual information and social context information. We perform experiments on large scale real world dataset of news articles, and use Twitter as the platform providing information about the social context of these news articles. We compare with and outperform several state-of-the-art baselines. Our conclusion is that using the social context information is most useful when faced with topics that are particularly difficult to detect.

One important challenge of current search engines is to satisfy the users' needs when they provide a poorly formulated query. When the pages matching the user's original keywords are judged to be unsatisfactory, query recommendation techniques are used to propose alternative queries and alter the result set. These techniques search for queries that are semantically similar to the user's original query, often searching for keywords that are similar to the keywords given by the user. However, when the original query is sufficiently ill-posed, the user's informational need is best met using entirely different keywords, and a substantially different query may be necessary.

Collaborative content creation and annotation creates vast repositories of all sorts of media, and user-defined tags play a central role as they are a simple yet powerful tool for organizing, searching and exploring the available resources. We observe that when a user annotates a resource with a set of tags, those tags are introduced one at a time. Therefore, when the fourth tag is introduced, a knowledge represented by the previous three tags, i.e., the context in which the fourth tag is produced, is available and exploitable for generating potential correction of the current tag. This context, together with the "wisdom of the crowd" represented by the co-occurrences of tags in all the resources of the repository, can be exploited to provide interactive tag spell check and correction. We develop this idea in a framework, based on a weighted tag co-occurrence graph and on nodes relatedness measures defined on weighted neighborhoods. We test our proposal on a dataset coming from YouTube. The results show that our framework is effective as it outperforms two important baselines. We also show that it is efficient, thus enabling its use in modern tagging services.

In this paper we introduce the task of "tweet recommendation", the problem of suggesting tweets that match a user's interests and likes. We propose an Information-Retrieval-like model that leverages the content of the user's tweets and those of her friends, and that effectively retrieves a set of tweets that is personalized and varied in nature. Our approach could be easily leveraged to build, for example, a Twitter or Facebook timeline that collects messages that are of interest for the user, but that are not posted by her friends. We compare to typical approaches used in similar tasks, reporting significant gains in terms of overall precision, up to about +20%, on both a corpus-based evaluation and real world user study.

We present a recommendation method based on the well-known concept of center-piece subgraph, that allows for the time/space efficient generation of suggestions also for rare, i.e., long-tail queries. Our method is scalable with respect to both the size of datasets from which the model is computed and the heavy workloads that current web search engines have to deal with. Basically, we relate terms contained into queries with highly correlated queries in a query-flow graph. This enables a novel recommendation generation method able to produce recommendations for approximately 99% of the workload of a real-world search engine. The method is based on a graph having term nodes, query nodes, and two kinds of connections: term-query and query-query. The first connects a term to the queries in which it is contained, the second connects two query nodes if the likelihood that a user submits the second query after having issued the first one is sufficiently high. On such large graph we need to compute the center-piece subgraph induced by terms contained into queries. In order to reduce the cost of the above computation, we introduce a novel and efficient method based on an inverted index representation of the model. We experiment our solution on two real-world query logs and we show that its effectiveness is comparable (and in some case better) than state-of-the-art methods for head-queries. More importantly, the quality of the recommendations generated remains very high also for long-tail queries, where other methods fail even to produce any suggestion. Finally, we extensively investigate scalability and efficiency issues and we show the viability of our method in real world search engines.