@conference{Balog2020,

title = {Measuring Recommendation Explanation Quality: The Conflicting Goals of Explanations},

author = {Krisztian Balog and Filip Radlinski},

url = {https://dl.acm.org/doi/pdf/10.1145/3397271.3401032},

doi = {https://doi.org/10.1145/3397271.3401032},

year  = {2020},

date = {2020-07-01},

booktitle = {Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR '20)},

pages = {329–338},

address = {New York},

abstract = {Explanations have a large effect on how people respond to recommendations. However, there are many possible intentions a system may have in generating explanations for a given recommendation -from increasing transparency, to enabling a faster decision, to persuading the recipient. As a good explanation for one goal may not be good for others, we address the questions of (1) how to robustly measure if an explanation meets a given goal and (2) how the different goals interact with each other. Specifically, this paper presents a first proposal of how to measure the quality of explanations along seven common goal dimensions catalogued in the literature. We find that the seven goals are not independent, but rather exhibit strong structure. Proposing two novel explanation evaluation designs, we identify challenges in evaluation, and provide more efficient measurement approaches of explanation quality.},

note = {Pre SFI},

keywords = {HCI design and evaluation methods, Human-centered computing, Information Systems, Recommender systems, WP2: User Modeling Personalization and Engagement},

pubstate = {published},

tppubtype = {conference}

}

@conference{Starke2020b,

title = {With a little help from my peers: depicting social norms in a recommender interface to promote energy conservation},

author = {Alain D. Starke and Martijn C. Willemsen and Chris C.P. Snijders},

url = {https://dl.acm.org/doi/10.1145/3377325.3377518},

doi = {10.1145/3377325.3377518},

year  = {2020},

date = {2020-03-17},

number = {March 2020},

pages = {1-11},

abstract = {How can recommender interfaces help users to adopt new behaviors? In the behavioral change literature, nudges and norms are studied to understand how to convince people to take action (e.g. towel re-use is boosted when stating that `75% of hotel guests' do so), but what is advised is typically not personalized. Most recommender systems know what to recommend in a personalized way, but not much research has considered how to present such advice to help users to change their current habits. We examine the value of presenting normative messages (e.g. `75% of users do X') based on actual user data in a personalized energy recommender interface called `Saving Aid'. In a study among 207 smart thermostat owners, we compared three different normative explanations (`Global', `Similar', and `Experienced' norm rates) to a non-social baseline (`kWh savings'). Although none of the norms increased the total number of chosen measures directly, we show evidence that the effect of norms seems to be mediated by the perceived feasibility of the measures. Also, how norms were presented (i.e. specific source, adoption rate) affected which measures were chosen within our Saving Aid interface.},

keywords = {Decision Support System, Human computer interaction, Human-centered computing, Information Systems, User studies},

pubstate = {published},

tppubtype = {conference}

}

@conference{Dacrema2019,

title = {Are We Really Making Much Progress? A Worrying Analysis of Recent Neural Recommendation Approaches},

author = {Maurizio Ferrari Dacrema and Paolo Cremonesi and Dietmar Jannach},

url = {https://arxiv.org/pdf/1907.06902.pdf},

year  = {2019},

date = {2019-08-16},

booktitle = {Proceedings of the 2019 ACM Conference on Recommender Systems (RecSys 2019)},

address = {Copenhagen},

abstract = {Deep learning techniques have become the method of choice for

researchers working on algorithmic aspects of recommender systems. With the strongly increased interest in machine learning in

general, it has, as a result, become difficult to keep track of what

represents the state-of-the-art at the moment, e.g., for top-n recommendation tasks. At the same time, several recent publications

point out problems in today’s research practice in applied machine

learning, e.g., in terms of the reproducibility of the results or the

choice of the baselines when proposing new models.

In this work, we report the results of a systematic analysis of algorithmic proposals for top-n recommendation tasks. Specifically,

we considered 18 algorithms that were presented at top-level research conferences in the last years. Only 7 of them could be reproduced with reasonable effort. For these methods, it however

turned out that 6 of them can often be outperformed with comparably simple heuristic methods, e.g., based on nearest-neighbor or

graph-based techniques. The remaining one clearly outperformed

the baselines but did not consistently outperform a well-tuned nonneural linear ranking method. Overall, our work sheds light on a

number of potential problems in today’s machine learning scholarship and calls for improved scientific practices in this area.},

note = {Pre SFI},

keywords = {Collaborative filtering, General and referance, Information Systems, Recommender systems, WP2: User Modeling Personalization and Engagement},

pubstate = {published},

tppubtype = {conference}

}

@conference{Starke2017,

title = {Effective User Interface Designs to Increase Energy-efficient Behavior in a Rasch-based Energy Recommender System},

author = {Alain D. Starke and Martijn C. Willemsen and Chris C.P. Snijders},

url = {https://dl.acm.org/doi/abs/10.1145/3109859.3109902},

doi = {10.1145/3109859.3109902},

year  = {2017},

date = {2017-08-27},

number = {August 2017},

pages = {1-9},

abstract = {People often struggle to find appropriate energy-saving measures to take in the household. Although recommender studies show that tailoring a system's interaction method to the domain knowledge of the user can increase energy savings, they did not actually tailor the conservation advice itself. We present two large user studies in which we support users to make an energy-efficient behavioral change by presenting tailored energy-saving advice. Both systems use a one-dimensional, ordinal Rasch scale, which orders 79 energy-saving measures on their behavioral difficulty and link this to a user's energy-saving ability for tailored advice. We established that recommending Rasch-based advice can reduce a user's effort, increase system support and, in turn, increase choice satisfaction and lead to the adoption of more energy-saving measures. Moreover, follow-up surveys administered four weeks later point out that tailoring advice on its feasibility can support behavioral change.},

keywords = {Applied computing, Human-centered computing, Information Systems},

pubstate = {published},

tppubtype = {conference}

}

@conference{Elahi2017,

title = {Exploring the semantic gap for movie recommendations},

author = {Mehdi Elahi and Yashar Deldjoo and Farshad Bakhshandegan Moghaddam and Leonardo Cella and Stefano Cerada and Paolo Cremonesi },

url = {https://dl.acm.org/doi/pdf/10.1145/3109859.3109908},

doi = {https://doi.org/10.1145/3109859.3109908},

year  = {2017},

date = {2017-08-01},

booktitle = {Proceedings of the Eleventh ACM Conference on Recommender Systems},

pages = {326–330},

address = {New York},

organization = {Association for Computing Machinery},

abstract = {In the last years, there has been much attention given to the semantic gap problem in multimedia retrieval systems. Much effort has been devoted to bridge this gap by building tools for the extraction of high-level, semantics-based features from multimedia content, as low-level features are not considered useful because they deal primarily with representing the perceived content rather than the semantics of it.



In this paper, we explore a different point of view by leveraging the gap between low-level and high-level features. We experiment with a recent approach for movie recommendation that extract low-level Mise-en-Scéne features from multimedia content and combine it with high-level features provided by the wisdom of the crowd.



To this end, we first performed an offline performance assessment by implementing a pure content-based recommender system with three different versions of the same algorithm, respectively based on (i) conventional movie attributes, (ii) mise-en-scene features, and (iii) a hybrid method that interleaves recommendations based on movie attributes and mise-en-scene features. In a second study, we designed an empirical study involving 100 subjects and collected data regarding the quality perceived by the users. Results from both studies show that the introduction of mise-en-scéne features in conjunction with traditional movie attributes improves both offline and online quality of recommendations.},

note = {Pre SFI},

keywords = {Information Systems, Recommender systems, WP2: User Modeling Personalization and Engagement},

pubstate = {published},

tppubtype = {conference}

}