Denis Kotkov

A survey of serendipity in recommender systems

We summarize most efforts on serendipity in recommender systems.We compare definitions of serendipity in recommender systems.We classify the state-of-the-art serendipity-oriented recommendation algorithms.We review methods to assess serendipity in recommender systems.We provide the future directions of serendipity in recommender systems. Recommender systems use past behaviors of users to suggest items. Most tend to offer items similar to the items that a target user has indicated as interesting. As a result, users become bored with obvious suggestions that they might have already discovered. To improve user satisfaction, recommender systems should offer serendipitous suggestions: items not only relevant and novel to the target user, but also significantly different from the items that the user has rated. However, the concept of serendipity is very subjective and serendipitous encounters are very rare in real-world scenarios, which makes serendipitous recommendations extremely difficult to study. To date, various definitions and evaluation metrics to measure serendipity have been proposed, and there is no wide consensus on which definition and evaluation metric to use. In this paper, we summarize most important approaches to serendipity in recommender systems, compare different definitions and formalizations of the concept, discuss serendipity-oriented recommendation algorithms and evaluation strategies to assess the algorithms, and provide future research directions based on the reviewed literature.

Challenges of Serendipity in Recommender Systems

Most recommender systems suggest items similar to a user profile, which results in boring recommendations limited by user preferences indicated in the system. To overcome this problem, recommender systems should suggest serendipitous items, which is a challenging task, as it is unclear what makes items serendipitous to a user and how to measure serendipity. The concept is difficult to investigate, as serendipity includes an emotional dimension and serendipitous encounters are very rare. In this paper, we discuss mentioned challenges, review definitions of serendipity and serendipity-oriented evaluation metrics. The goal of the paper is to guide and inspire future efforts on serendipity in recommender systems.

Cross-Social Network Collaborative Recommendation

Online social networks have become an essential part of our daily life, and an increasing number of users are using multiple online social networks simultaneously. We hypothesize that the integration of data from multiple social networks could boost the performance of recommender systems. In our study, we perform cross-social network collaborative recommendation and show that fusing multi-source data enables us to achieve higher recommendation performance as compared to various single-source baselines.

Cross-Domain Recommendations with Overlapping Items

In recent years, there has been an increasing interest in cross-domain recommender systems. However, most existing works focus on the situation when only users or users and items overlap in different domains. In this paper, we investigate whether the source domain can boost the recommendation performance in the target domain when only items overlap. Due to the lack of publicly available datasets, we collect a dataset from two domains related to music, involving both the users’ rating scores and the description of the items. We then conduct experiments using collaborative filtering and content-based filtering approaches for validation purpose. According to our experimental results, the source domain can improve the recommendation performance in the target domain when only items overlap. However, the improvement decreases with the growth of non-overlapping items in different domains.

Investigating serendipity in recommender systems based on real user feedback

Over the past several years, research in recommender systems has emphasized the importance of serendipity, but there is still no consensus on the definition of this concept and whether serendipitous items should be recommended is still not a well-addressed question. According to the most common definition, serendipity consists of three components: relevance, novelty and unexpectedness, where each component has multiple variations. In this paper, we looked at eight different definitions of serendipity and asked users how they perceived them in the context of movie recommendations. We surveyed 475 users of the movie recommender system, MovieLens regarding 2146 movies in total and compared those definitions of serendipity based on user responses. We found that most kinds of serendipity and all the variations of serendipity components broaden user preferences, but one variation of unexpectedness hurts user satisfaction. We found effective features for detecting serendipitous movies according to definitions that do not include this variation of unexpectedness. We also found that different variations of unexpectedness and different kinds of serendipity have different effects on preference broadening and user satisfaction. Among movies users rate in our system, up to 8.5% are serendipitous according to at least one definition of serendipity, while among recommendations that users receive and follow in our system, this ratio is up to 69%.

Volkswagen Emission Crisis – Managing Stakeholder Relations on the Web

Organizations establish their own profiles at social media sites to publish pertinent information to customers and other stakeholders. During a long and severe crisis, multiple issues may emerge in media interaction. Positive responses and prompt interaction from the official account of e.g. a car manufacturer creates clarity and reduces anxiety among stakeholders. This research targets the Volkswagen 2015 emission scandal that became public on Sept. 18, 2015. We report its main phases over time based on public web information. To better understand the online interaction and reactions of the company, we scrutinized what information was published on VW’s official web sites, Facebook, and Twitter profiles and how the image of the company developed over time among various stakeholders. To investigate this, Twitter and Facebook data sets were collected, cleaned, and analysed. We also compared this crisis in several respects with the Toyota recall crisis in 2010-2011 that was caused by sticking accelerator pedals and floor mats, as well as the GM crisis in 2014 that was caused by faulty ignition switches. Further we compare our findings with the Malaysian airline crisis that was caused by the disappeared flight MH370 and downed MH14.

A Serendipity-Oriented Greedy Algorithm for Recommendations

Most recommender systems suggest items to a user that are popular among all users and similar to items the user usually consumes. As a result, a user receives recommendations that she/he is already familiar with or would find anyway, leading to low satisfaction. To overcome this problem, a recommender system should suggest novel, relevant and unexpected, i.e. serendipitous items. In this paper, we propose a serendipity-oriented algorithm, which improves serendipity through feature diversification and helps overcome the overspecialization problem. To evaluate our algorithm and compare it with others, we employ a serendipity metric that captures each component of serendipity, unlike the most common metric.

Recommending Serendipitous Items using Transfer Learning

Most recommender algorithms are designed to suggest relevant items, but suggesting these items does not always result in user satisfaction. Therefore, the efforts in recommender systems recently shifted towards serendipity, but generating serendipitous recommendations is difficult due to the lack of training data. To the best of our knowledge, there are many large datasets containing relevance scores (relevance oriented) and only one publicly available dataset containing a relatively small number of serendipity scores (serendipity oriented). This limits the learning capabilities of serendipity oriented algorithms. Therefore, in the absence of any known deep learning algorithms for recommending serendipitous items and the lack of large serendipity oriented datasets, we introduce SerRec our novel transfer learning method to recommend serendipitous items. SerRec uses transfer learning to firstly train a deep neural network for relevance scores using a large dataset and then tunes it for serendipity scores using a smaller dataset. Our method shows benefits of transfer learning for recommending serendipitous items as well as performance gains over the state-of-the-art serendipity oriented algorithms

Samsung and Volkswagen Crisis Communication in Facebook and Twitter : A Comparative Study

Since September 2015 at least two major crises have emerged where major industrial companies producing consumer products have been involved. In September 2015 diesel cars manufactured by Volkswagen turned out to be equipped with cheating software that caused NO2 and other emission values to be reduced to acceptable levels while tested from the real, unacceptable values in normal use. In August 2016 reports began to appear that the battery of a new smart phone produced by Samsung, Galaxy Note7, could begin to burn, or even explode, while the device was on. In Nov. 2016 also 34 washing machine models were reported to have caused damages due to disintegration. In all cases, the companies have experienced substantial financial losses, their shares have lost value, and their reputation has suffered among consumers and other stakeholders. In this paper, we study the commonalities and differences in the crisis management strategies of the companies, mostly concentrating on the crisis communication aspects. We draw on Situational Crisis Communication Theory (SCCT). The communication behaviour of the companies and various stakeholders during crisis is performed by investigating the official web sites of the companies and communication in Twitter and Facebook on their own accounts. We also collected streaming data from Twitter where Samsung and the troubled smart phone or washing machines were mentioned. For VW we also collected streaming data where the emission scandal or its ramifications were mentioned and performed several analyses, including sentiment analysis.

Improving Serendipity and Accuracy in Cross-Domain Recommender Systems

Cross-domain recommender systems use information from source domains to improve recommendations in a target domain, where the term domain refers to a set of items that share attributes and/or user ratings. Most works on this topic focus on accuracy but disregard other properties of recommender systems. In this paper, we attempt to improve serendipity and accuracy in the target domain with datasets from source domains. Due to the lack of publicly available datasets, we collect datasets from two domains related to music, involving user ratings and item attributes. We then conduct experiments using collaborative filtering and content-based filtering approaches for the purpose of validation. According to our results, the source domain can improve serendipity in the target domain for both approaches. The source domain decreases accuracy for content-based filtering and increases accuracy for collaborative filtering. The improvement of accuracy decreases with the growth of non-overlapping items in different domains.