Recommendation system (RS) is designed to provide personalized services based on the users’ historical data. It has been applied in various fields and is expected to recommend the suitable services ...for the different kinds of users. Considering the importance of individual privacy, current users gradually tend not to expose personal information. This means RS may face the highly sparse datasets in the fields of cloud security. In general, the accuracy of recommendation will be improved with the growth of individual data, but the cold start problem is exactly in this contradictory phenomenon: this question evolves to produce sufficiently accurate recommendation result under the data scarcity problem. RS has to recommend services for the rarely historical data users and the latent users might drain along with the production of counter effects. To alleviate data scarcity problem in cloud security environment, this work is to introduce similar domain knowledge based on the transfer learning. Besides, the content and location based methods have been proved that these ideas work under this situation. So, this work also employs latent dirichlet allocation (LDA) to analysis the service descriptions and explore the relationship between the content and location information. In this framework, the suitable combination of LDA and word2vec models will balance the accuracy and speed which benefit service recommendation particularly. The related experiments demonstrate the effectiveness on the real word dataset. It can be found that the transfer learning based word2vec model shows the potentiality to explore the relationship between topic words, and improve the LDA algorithm from the content relationship. This proves that in both cold start environment and warm start environment, the proposed algorithm is more robust than other model-based state-of-art methods.
•The selection strategy of MCDA methods is redefined.•A new methodology and decision support system is proposed to recommend MCDA methods.•The most comprehensive nowadays database of 200+ MCDA ...methods has been created.•Decision analysts can be guided while leading complex decision-making processes.•Some methodological mistakes in the selection of the MCDA methods are unveiled.
We present a new methodology to lead the selection of Multiple Criteria Decision Analysis (MCDA) methods. It is implemented in the Multiple Criteria Decision Analysis Methods Selection Software (MCDA-MSS), a decision support system that helps analysts answer a recurring question in decision science: “Which is the most suitable Multiple Criteria Decision Analysis method (or a subset of MCDA methods) that should be used for a given Decision-Making Problem (DMP)?”. The MCDA-MSS provides guidance to lead decision-making processes and choose among an extensive collection (>200) of MCDA methods. These are assessed according to an original comprehensive set of problem characteristics. The accounted features concern problem formulation, preference elicitation and types of preference information, desired features of a preference model, and construction of the decision recommendation. The applicability of the MCDA-MSS has been tested on several case studies. The MCDA-MSS includes the capabilities of (i) covering from very simple to very complex DMPs, (ii) offering recommendations for DMPs that do not match any method from the collection, (iii) helping analysts prioritize efforts for reducing gaps in the description of the DMPs, and (iv) unveiling methodological mistakes that occur in the selection of the methods. A community-wide initiative involving experts in MCDA methodology, analysts using these methods, and decision-makers receiving decision recommendations will contribute to the expansion of the MCDA-MSS.
Display omitted
Artificial intelligence chatbots such as ChatGPT (OpenAI) have garnered excitement about their potential for delegating writing tasks ordinarily performed by humans. Many of these tasks (eg, writing ...recommendation letters) have social and professional ramifications, making the potential social biases in ChatGPT's underlying language model a serious concern.
Three preregistered studies used the text analysis program Linguistic Inquiry and Word Count to investigate gender bias in recommendation letters written by ChatGPT in human-use sessions (N=1400 total letters).
We conducted analyses using 22 existing Linguistic Inquiry and Word Count dictionaries, as well as 6 newly created dictionaries based on systematic reviews of gender bias in recommendation letters, to compare recommendation letters generated for the 200 most historically popular "male" and "female" names in the United States. Study 1 used 3 different letter-writing prompts intended to accentuate professional accomplishments associated with male stereotypes, female stereotypes, or neither. Study 2 examined whether lengthening each of the 3 prompts while holding the between-prompt word count constant modified the extent of bias. Study 3 examined the variability within letters generated for the same name and prompts. We hypothesized that when prompted with gender-stereotyped professional accomplishments, ChatGPT would evidence gender-based language differences replicating those found in systematic reviews of human-written recommendation letters (eg, more affiliative, social, and communal language for female names; more agentic and skill-based language for male names).
Significant differences in language between letters generated for female versus male names were observed across all prompts, including the prompt hypothesized to be neutral, and across nearly all language categories tested. Historically female names received significantly more social referents (5/6, 83% of prompts), communal or doubt-raising language (4/6, 67% of prompts), personal pronouns (4/6, 67% of prompts), and clout language (5/6, 83% of prompts). Contradicting the study hypotheses, some gender differences (eg, achievement language and agentic language) were significant in both the hypothesized and nonhypothesized directions, depending on the prompt. Heteroscedasticity between male and female names was observed in multiple linguistic categories, with greater variance for historically female names than for historically male names.
ChatGPT reproduces many gender-based language biases that have been reliably identified in investigations of human-written reference letters, although these differences vary across prompts and language categories. Caution should be taken when using ChatGPT for tasks that have social consequences, such as reference letter writing. The methods developed in this study may be useful for ongoing bias testing among progressive generations of chatbots across a range of real-world scenarios.
OSF Registries osf.io/ztv96; https://osf.io/ztv96.
In this article we analyze the ethical aspects of multistakeholder recommendation systems (RSs). Following the most common approach in the literature, we assume a consequentialist framework to ...introduce the main concepts of multistakeholder recommendation. We then consider three research questions: Who are the stakeholders in a RS? How are their interests taken into account when formulating a recommendation? And, what is the scientific paradigm underlying RSs? Our main finding is that multistakeholder RSs (MRSs) are designed and theorized, methodologically, according to neoclassical welfare economics. We consider and reply to some methodological objections to MRSs on this basis, concluding that the multistakeholder approach offers the resources to understand the normative social dimension of RSs.
The problem of information overload motivated the appearance of Recommender Systems. From the several open problems in this area, the decision of which is the best recommendation algorithm for a ...specific problem is one of the most important and less studied. The current trend to solve this problem is the experimental evaluation of several recommendation algorithms in a handful of datasets. However, these studies require an extensive amount of computational resources, particularly processing time. To avoid these drawbacks, researchers have investigated the use of Metalearning to select the best recommendation algorithms in different scopes. Such studies allow to understand the relationships between data characteristics and the relative performance of recommendation algorithms, which can be used to select the best algorithm(s) for a new problem. The contributions of this study are two-fold: 1) to identify and discuss the key concepts of algorithm selection for recommendation algorithms via a systematic literature review and 2) to perform an experimental study on the Metalearning approaches reviewed in order to identify the most promising concepts for automatic selection of recommendation algorithms.
Fairness has become a critical value online, and the latest studies consider it in many problems. In recommender systems, fairness is important since the visibility of items is controlled by systems. ...Previous fairness-aware recommender systems assume that sufficient relationship data between users and items are available. However, it is common that new users and items are frequently introduced, and they have no relationship data yet. In this paper, we study recommendation methods to enhance fairness in a cold-start state. Fairness is more significant when the preference of a user or the popularity of an item is unknown. We propose a meta-learning-based cold-start recommendation framework called FaRM to alleviate the unfairness of recommendations. The proposed framework consists of three steps. We first propose a fairness-aware meta-path generation method to eliminate bias in sensitive attributes. In addition, we construct fairness-aware user representations through the meta-path aggregation approach. Then, we propose a novel fairness objective function and introduce a joint learning method to minimize the trade-off between relevancy and fairness. In extensive experiments with various cold-start scenarios, it is shown that FaRM is significantly superior in fairness performance while preserving relevance accuracy over previous work.
With the rapid development of Information Technology, there exist massive amounts of data available on the Internet, which result in a severe information overload problem. Especially, it becomes more ...and more challenging but necessary to help users find the contents or services that they really need. To address the problem mentioned above, recommender systems have been developed to exploit user’s historical behavior data and provide personalized services for promoting customer experiences in many fields, such as Point of Interest (POI) applications, multimedia services, and e-commerce websites. Specifically, in POI recommendation, user’s next check-in behaviors depend on both long- and short-term preferences. However, traditional recommendation methods often ignore the dynamic changes of user’s short-term preferences over time, which limits their performance. Besides, many existing methods cannot fully exploit the complex correlations and transitions between POI in check-ins sequences. In this paper, we propose an
A
ttentive
S
equential model based on
G
raph
N
eural
N
etwork (ASGNN) for accurate next POI recommendation. Specifically, ASGNN firstly models user’s check-in sequences as graphs and then use Graph Neural Networks (GNN) to learn the informative low-dimension latent feature vectors (embeddings) of POIs. Secondly, a personalized hierarchical attention network is adopted to exploit complex correlations between users and POIs in check-in sequences and capture user’s long- and short-term preferences. Finally, we perform the next POI recommendation via leveraging user’s long- and short-term preferences obtained from their behavior sequences with ASGNN. Extensive experiments are conducted on three real-world check-in datasets, and the results demonstrate that the proposed model ASGNN outperforms baselines, including some state-of-the-art methods.
Recommendation system has recently experienced widespread applications in fields like advertising and streaming platforms. Its ability of extracting valuable information from complex data makes it a ...promising tool for multi-modal transportation system. In this paper, we propose a conceptual framework for proactive travel mode recommendation combining recommendation system and transportation engineering. The proposed framework works by learning from historical user behavioral preferences and ranking the candidate travel modes. In this framework, an incremental scanning method with multiple time windows is designed to acquire multi-scale features from user behaviors. In addition, to alleviate the computational burden brought by the large data size, a hierarchical behavior structure is developed. To further allow for social benefits, the proposed framework proposes to adjust the candidate modes according to real-time traffic states, which is potential in promoting the use of public transport, alleviating traffic congestion, and reducing environmental pollution.