Meta-Intents in Conversational Recom mender Systems

Abstract

We present a study investigating the psychological characteristics of users and their conversation-related preferences in a conversational recommender system (CRS). We collected data from 260 participants on Prolific, using questionnaire responses concerning decision-making style, conversation-related feature preferences in the smartphone domain, and a set of metaintents, a concept we propose to represent high-level user preferences related to the interaction and decision-making in CRS. We investigated the relationship between users' decision-making style, meta-intents and feature preferences through Structural Equation Modeling. We find that decision-making style has a significant influence on meta-intents as well as on feature preferences, however, meta-intents do not have a mediating efect between these two factors, indicating that meta-intents are independent of item feature preferences and may thus be generalizable, domain-independent concepts. Our results provide evidence that the proposed meta-intents are linked to the general decision-making style of a user and can thus be instrumental in translating general decision-making factors into more concrete design guidance for CRS and their potential personalization. As meta-intents seem to be domain-independent factors, we assume meta-intents do not afect users' various interests in concrete product features and mainly reflect users' general decision-support needs and interaction preferences in CRS.

Keywords

• Decision-making style
• Meta intents
• Conversational UI design
• Conversational recommender systems

1. Introduction

Conversational recommender systems (CRS[ 1 ]) have try in recent years [ 2, 3 ]. Generally, conversational techniques can provide users with strong guidance to achieve their goals combined with a high level of flexibility in expressing their needs. Jannach et al. [ 4 ] distinguish between natural language-based, form-based, and criniques in recent years, natural language-based CRS have become subject of extensive research. Fu et al. [ 5 ] summarized NLP-based CRS into 3 paradigms: System is Active, (SAUE), System is Active, User is Active (SAUA). SAUA is a user-initiated paradigm of CRS, which provides the user with the greatest degree of flexibility, allowing the user and the system to lead the conversation, and be able to give appropriate feedback to the user’s questions. The appropriate feedback means answering user questions in a user-friendly style, but diferent users should have diferent preferences, e.g. preferring long sentences or

These are challenges for user-initiated CRS. SAUE and SAUP are system-initiated paradigms of

[ 6 ]. In this paper, we explore psychological characteristics of CRS users under two diferent objectives. First, we characteristics of CRS users, based on responses from questionnaire instruments. Here, we distinguish between stable individual traits including personality factors [ 7 ] and decision-making style [ 8 ], and, second, task-oriented characteristics that represent general user preferences when interacting with a CRS, such as obtaining detailed information about items or comparing products. We call the latter characteristics meta-intentions (or meta-intents short sentences, involving more technical details or not. aim at obtaining a deeper understanding of psychological © 2022 Copyright for this paper by its authors. Use permitted under Creative Commons License for short) since they describe user goals that are more Attribution 4.0 International (CC BY 4.0). general and high-level than the search goals typically ex- The disadvantage is that the question sequences/paths tracted through intent detection methods in CRS. Psycho- are hand-crafted, not enough freedom, and a lower-level logical factors are an important resource underutilized by personalization. current CRS. We therefore propose an initial framework Critiquing-based CRS will first recommend options that includes the psychological factors in CRS design, and and then elicit users’ feedback in the form of critiques also describes our core research target, the meta-intents [16], It help users to eficiently refine their preference in it (Figure 1). As a second objective, we investigate by providing more options, but on the other hand, it can the relations between psychological user characteristics be frustrating for novice users because they are overand users’ interests in product topics in a conversational whelmed by so many parameter options without really scenario. understanding what those parameters really mean. Ma

In this paper, we describe a study analyzing these ques- et al. [17] proposed mixing language, GUI elements to imtions and present its results. Our contribution is: we prove user experience in CRS. However, it poses a greater provide insights about CRS users’ decision-making style challenge to the design of the CRS as well. (rational vs. intuitive) and its influence on the diferent Currently, very limited research has as yet studied meta-intents that we propose, as well as about the re- users’ psychological influence in CRS and related design lation between decision style, meta-intents, and users’ questions. For example, Papenmeier et al. [18] investiinterest in product-specific features/topics. For this pur- gated human advisory dialogs, identifying some recurpose we present an analysis using Structural Equation ring strategies such as funneling to successively narrow Modeling. down the space of potential items. Kleemann et al. [19] investigated user behavior and personal characteristics when using a advisor in combination with other deci2. Related work sion aids, and studied various supporting methods’ (chatbot, advisor, filter, recommendation) popularity, utilizaConversational Recommender Systems (CRS) have be- tion, and switching rate between each other [20]. Atas come a rapidly growing and popular research area be- et al. [21] summarize that preferences are determined cause they provide a flexible, human-like multi-turn dia- and adapted is influenced by various factors such as perlog for preference elicitation, which is essential for gen- sonality traits, emotional states, and cognitive biases. erating personalized recommendations [9]. Jannach et al. To provide design guidance for CRS and to potentially [ 4 ] distinguish three types of CRS, difering in the style adapt them to the individual user, a deeper understanding and structure of the interaction used: natural language- of the psychological factors influencing users’ decision based, form-based, and critiquing-based. making and interaction behavior in CRS is required. For

NLP-based CRS have received considerable interest recommender systems in general, the influence of psychorecently due to the advancements in natural language logical characteristics on users’ preference construction processing. They typically use a question-answer format and decision making has been shown repeatedly [21]. Lex Zhang et al. [10]. As the mainstream, it has developed et al. [22] distinguish between factors related to cognition, vigorously in recent years, e.g. Sun and Zhang [ 1 ] import personality, and emotion. The influence of psychological the end-to-end reinforcement learning model to CRS, characteristics such as the Big Five personality factors Zhang et al. [11] combine contextual bandits method (e.g. [23, 24]), Need for Cognition [25], or cognitive bito improve preference elicitation and recommendation ases [26] has been studied in several works. However, performance. Zhou et al. [12] utilize knowledge graph- these studies mostly aim at better understanding user based as an external knowledge to enhance CRS, Li et al. preferences with respect to the recommended items and [13] unifying items and features in same arm space, use at improving their accuracy. In contrast, the relationship bandits method to facilitate cold-start problem in CRS, between psychological factors and the design of advisory Zhou et al. [14] extract topic threads from their dataset dialogs in CRS remains an underexplored area. Especially and leverage it to increase utility and user acceptability theories related to human decision-making styles appear of CRS. NLP-based CRS provides the greatest freedom, to be promising points of departure for studying this allowing users to express freely, while misunderstandings relation. The distinction between rational and intuitive can also usually happen and lead to user frustration. decision-making styles [27] or cognitive styles such as

Form-based CRS present questions and answer in the need for cognition may influence users’ assessment a GUI style, leading users through a predefined dialog of CRS. More domain-specific theories such as Shopping structure. This type of CRS has many advantages as Orientation [28, 29], distinguishing between task-focused they provide guidance to the users, avoid errors, and and experiential shopping are also of interest. However, can incorporate domain knowledge. Especially usage- none of these approaches has yet been applied to CRS. related questions are important for users who have only User goals and preferences when interacting with a limited knowledge about technical item properties [15]. CRS may be located on diferent levels of abstraction.

Low-level preferences refer to concrete properties of the

desired item (often called intents in CRS, specifically Add Details [30]). Jameson et al. [31] suggest high-level factors (such as economy and safety) but these factors are related to the product itself, not to the way users prefer to interact with a CRS. On a more abstract level, metalevel preferences that relate to the conversation and type of questions in a CRS have, to our knowledge, not been studied yet.

3. User characteristics and meta-intents

To investigate diferences in CRS users’ psychological

properties, we hypothesized that decision-making style might influence users’ usage and interaction in CPA. Accordingly, we applied instruments to measure these properties, using the Decision Styles Scale (DSS) [27] for distinguishing rational and intuitive decision-making.

While general decision-making styles, e.g. rational and intuitive, apply to arbitrary decision contexts, we also aimed at capturing users’ preferences at a more specific, yet still abstract level. These meta-intents should bridge the gap between item-level intents and general decisionmaking style, and should also relate to the design and question-asking style in CRS. They might also be relevant for more general recommendation scenarios. We postulated the following set of meta-intents (with sample questionnaire items in parentheses), partly related to general usage factors such as eficiency, efectiveness, and user guidance. We see this list as a first step towards defining factors relevant for users’ decision-making process in CRS which is neither complete nor final.

• Eficiency orientation (For me, finding a suitable product quickly is more important than exploring all options.) • Diversity orientation (When shopping online,

I tend to explore a diverse range of products that might interest me.) • Goal focus (I usually have a clear idea of what

I want before visiting an online shop. I often only make up my mind once I see the available choices.) • Openness for guidance (I appreciate it if a shop

recommends products I might like.) • Interest in detail (I usually gather as much information as possible about products that I want to buy. I am interested in detailed information about products.) • Human-like (I would like a human-like conver

sation with an advisor system such as a chatbot.) • Comparison orientation (Comparing the features of diferent candidate products is important for me.) • Scope of choice (When the system recommends products, I rather like to see a longer list rather than a short one.)

The CRS framework we propose incorporates psychological level factors and preferences that relate to the items and their properties (topic preferences and value preferences) as shown in Figure 1. We first introduce what each part represents. The decision style shown on the left side as main characteristic factors that might influence meta-intents and users’ feature preferences which are in the middle part of the figure. Here we use the term topics instead of features to emphasize that in the CRS, the user’s preference is not only about product features but also the user experience, usage, and other higher abstract level topics. For example, asking user questions about the resolution of the main camera (feature level), or taking good pictures (usage level), or the quality of the main camera (assessment level) all belong to topic preference elicitation. Users’ interest in product features/topics is abbreviated as topic preference below.

The right part of the Figure 1 refers to a conventional Figure 2: Our structural equation model that includes 3 parts, CRS model which can be, for example, CRM model [ 1 ] stable psychological traits (decision-making style), the proor EAR model [32] (which are 2 popular CRS models posed psychological traits (meta-intents) and topic preference that include conversation function and recommendation (smartphone domain). function and utilized deep neural networks). The top element of the middle part is meta-intents which solves the problem how to ask and respond and can be used to guide 4.1. Method the interaction style of CRS. Topic preference is related to the interactive content (ask which topic) and can be We first presented participants with a scenario in which used to improve the preference elicitation process. Value they were supposed to buy a new smartphone, and then preference which stands for the users’ personalized pref- started our questionnaire. The smartphone domain was erence value for one specific feature/topic. The middle chosen because it requires a suficiently complex decipart, topic preference and value preference are also known sion process, involving a variety of decision criteria. For as intents detection which is an active area of research in most people it is also a well-known, real-life task that NLP-based CRS. We decouple intents detection into two requires understanding the product features at least to elements here for studying the impact of decision-making a certain extent. Furthermore, it has a large number of style on it. Our framework proposes that psychological feature options. To measure psychological characterischaracteristics can be treated as additional knowledge tics, we applied the existing Decision Style Scale (DSS) to improve CRS design, so in this paper, we apply SEM questionnaire [27] as well as a self-developed questionto analyze how does psychological characteristic impact naire on meta-intents (Section 3), both with 5-point Likert these factors and our research can be boiled down to two scales. To measure topic preference, we collected a total questions: of 27 topics in the smartphone domain, including 4 different levels: usage-level, general-level, technical-level, • Does decision-making style significantly influ- and professional-level, as shown in Table 1. There were ence users’ meta-intents and topic preference? short descriptions for some less well-known topics in our questionnaire, e.g. network sensitivity (signal strength, • Do meta-intents have a mediation efect between how easy is it to connect to a mobile network). We asked decision-making style and topic preference? participants to rate each topic on a 5-point Likert scale according to their interest (1: don’t care, 5: very interested 4. Study in), along with an unknown option, in case participants did not understand the topic’s meaning.

To investigate CRS users’ psychological characteristics, both at the level of decision-making style and metaintentions, as well as possible relations with their topic preference, we conducted an online survey in which participants were presented a scenario involving the purchase of a new smartphone and answered questionnaires concerning their product-related preferences as well as their psychological characteristics. We hypothesized that general traits (decision-making style) significantly influence meta-intents and topic preference. We also assumed that meta-intents might have a mediating efect between decision-making style and users’ topic preference .

4.2. Participants

We recruited 278 participants using Prolific 1, a tool commonly used for academic surveys [33], of whom 275 finished the study. In our analysis, we only considered participants who passed 3 inner attention test questions (e.g. , It’s an attention test, please select strongly agree), leaving us with 260 participants. 143 of the 260 participants were female. Their age ranged from 19 to 75 (M = 38.42, SD = 12.60). We pre-selected Prolific users based on the following criteria to maximize quality: (1) participants should be fluent in English; (2) their success rate should be greater than 95 %. The average duration of the survey was 5.56 minutes (SD = 2.48) and each participant received compensation of 0.75£ if they successfully completed the survey.

5. Results

We applied Structural Equation Modeling (SEM) to our dataset for estimating and testing the causal efects of three main variables: Decision-making style, metaintents and topic preference. Since DSS is a wellestablished, validated questionnaire and meta-intents are captured with single-items (each factor has only one question), we could directly incorporate both in our proposed model (see Figure 2). Concerning topic preference, on the other hand, a total of 27 topics (items) with assumed commonalities have been asked, e.g. taking photo video (usage), number of main cameras (technical) and main camera resolution (professional) should involve correlated rating patterns, hence presumably loading onto the same factor. Therefore, we do not treat all 27 topics as single independent variables but apply Exploratory Factor Analysis (EFA) to extract conjoint latent variables that can subsequently be fed into our proposed SEM model. mine the number of factors. We ran the EFA recursively such that after the first epoch, resulting in dropping one item, a second run finally met the requirements. We ifltered out seven topics in total: screen resolution (fac5.1. EFA on topic preference tor loadings < 0.4), price performance ratio (single item factor), biometric unlock (single item factor), multi apps The scores for topic preference are derived from a set of (factor loadings < 0.4), headset jack 35 (single item factor), 260 valid participants’ ratings of 27 smartphone topics. take photo and video and smartphone game (Cronbach’s 63 of them tagged at least one topic as unknown (see < 0.6). Finally, we extracted six factors from 22 topics. We Figure 3). Thereby, we found that the more technical the name these factors according to the topics they represent: topic, the fewer people could grasp its meaning. Finally, camera, reliability, novelty, design, memory storage, and only 197 participants’ data could be used for the EFA technical. The cumulative variance of 6 factors is 66.35 %, analysis. all of them having a factor loading over 0.4, commonality

First, we performed prerequisite tests for EFA, the over 0.49, Cronbach’s over 0.60. Details are shown in Kaiser-Meyer-Olkin (KMO) value is .796 (> 0.7) and Table 2.

Bartlett’s test is significant ( < .001), which both indicate that our data meets the requirements for performing EFA. Next, we used Principal Component Analysis (PCA) to extract factors, with Varimax rotation and Kaiser Normalization, taking eigenvalue > 1 as the threshold to deter

5.2. SEM on decision-making style,

meta-intents, topic preference 5.2.1. Part A: decision-making style and meta-intents Finally, based on our data, we constructed a SEM, which Part A focuses on the influence of decision-making style contains decision-making style, meta-intents and topic on meta-intents. After removing non-significant efects, preference, as shown in Figure 4. Decision-making style ifve of eight meta-intents factors remain. We found the (ovals) and topic preference (ovals) are estimated from factor rationality having significant influences on five several directly measurable questionnaire items. In order meta-intents factors with the greatest impact on interest to display the relationships between our main factors in details (0.61) and comparison oriented (0.47). Besides as clearly as possible, we leave out the factor loadings these relationships, rationality also has positive influof concrete questionnaire items. Decision-making style ences on diversity orientation (0.22) and scope of choice and meta-intents are latent variables in this framework, (0.26), but a negative influence on eficiency orientation however, since the meta-intents are measured by a single (-0.29). In contrast, for the intuitiveness factor only a question, we use rectangles to represent them. The ar- single significant (positive) efect on eficiency orientation rows indicate significant influences, with the value above (0.34) could be identified. depicting standardized regression coeficients, while nonsignificant connections have been removed for clarity. 5.2.2. Part B: decision-making style and topic As the entire SEM is quite large, in order to analyze it preference methodically, we split it into two parts with the green rounded rectangle representing Part A, and the yellow rounded rectangle representing Part B respectively.

Part B focuses on the influence of decision-making style on topic preference. After cleaning the non-significant efects, four of six topic preference factors remain. We found the rationality has positive and significant influences on camera (0.27), memory storage (0.31), and technical (0.26). The intuitiveness has positive and significant influences on camera (0.46), reliability (0.34), memory 6. Discussion

Concerning Part B, we notice that the intuitiveness has larger standardized regression coeficients (0.46) on camera than the rationality (0.27) implying that intuitive people are more interested in camera functionality than rational people. This gives us some pointers for CRS design in this specific domain. When eliciting preferences (or detecting intents), camera is a topic of interest to the user with high intuition. From a more general point of view, the discrepancies between rational and intuitive decision makers suggest that the former are more focused on the low-level technical specifics of a product domain (such as the CPU which is installed in a smartphone), while the latter are more attracted to information about immediately experiential properties (such as the quality of a shot photo).

Our findings provide insights into intent detection for

6.3. Overall model

CRS in preference elicitation. Supposing data on users’ translating general decision-making factors into more decision-making styles are available, the survey results concrete design guidance for CRS and their potential percan provide a basis for personalizing the preference elic- sonalization. At the same time, we also point out three itation process, e.g. to help choosing which features to limitations of this experiment: 1. Meta-intents is a new ask and the order in which they are asked. At the same concept for which we used only one or two questionnaire time, we want to point out a limitation here. Unlike the items per intent. We plan to develop the instrument furhigh abstract level of meta-intents which can be applied ther and validate the meta-intents with a larger number to various fields, the findings here are based on a specific of questions. 2. The domain of this experiment is limited ifeld (smartphone). Still, we provide an idea for utilizing to smartphones, and comparative experiments in several decision-making knowledge to enhance the preference fields will be necessary in the future. 3. The integration elicitation process of CRS in a specific domain. of meta-intents into specific CRS models and the real impact of MI on user interaction needs to be explored in future work.

After applying SEM to the overall model, we found that the meta-intents factors do not significantly impact topic preference, which means our proposed meta-intents seem to be independent of product features and topics, and do not have mediating efects between decision-making style and topic preference. Meta-intents appear to be independent of our concrete product domain, but whether it is truly domain-independent remains to be verified by multi-domain research.

We believe our results provide some initial valuable insights that can help be better designe and possibly personalize CRS. In particular, we would like to point out that experiences with a CRS should be viewed from multiple perspectives. Diferences in individual decision behavior seem to be related not only to attitudes toward specific product features, but also to expectations of the interaction process as a whole. When designing a CRS, therefore, consideration should be given not only to personalizing the recommended products, but also to adapting the agent’s mode of communication. If both aspects are taken into account in an appropriate manner, it can be assumed that positive transfer efects could arise which, taken together, enrich the user’s overall experience.

7. Conclusion

In this paper, we propose a set of meta-intents factors, which can be seen as a bridge between classic psychological factors (decision-making style) and item-level intents, and which can be used as indicators of personalized UI design for CRS. We also propose a CRS framework that incorporates decision-making style, meta-intents factors, and conventional CRS models. This work uses SEM to validate the significant influence of decision-making style on meta-intents and topic preference. We also found that meta-intents seem to be domain-independent, dialogspecific factors that do not have a mediating efect on topic preference. Our results provide evidence that the proposed meta-intents are linked to the general decisionmaking style of a user and can thus be instrumental in [9] B. Lika, K. Kolomvatsos, S. Hadjiefthymiades, Fac- eling user interaction at the convergence of filtering the cold start problem in recommender sys- ing mechanisms, recommender algorithms and adtems, Expert Syst. Appl. 41 (2014) 2065–2073. visory components, in: Mensch Und Computer doi:1 0 . 1 0 1 6 / j . e s w a . 2 0 1 3 . 0 9 . 0 0 5 . 2021, MuC ’21, Association for Computing Ma[10] Y. Zhang, X. Chen, Q. Ai, L. Yang, W. B. Croft, To- chinery, New York, NY, USA, 2021, p. 499–511. wards conversational search and recommendation: doi:1 0 . 1 1 4 5 / 3 4 7 3 8 5 6 . 3 4 7 3 8 5 9 .

System ask, user respond, in: Proceedings of the [20] T. Kleemann, B. Loepp, J. Ziegler, Towards multi27th ACM International Conference on Information method support for product search and recomand Knowledge Management, CIKM ’18, Associa- mending, in: Adjunct Proceedings of the 30th tion for Computing Machinery, New York, NY, USA, ACM Conference on User Modeling, Adaptation 2018, p. 177–186. doi:1 0 . 1 1 4 5 / 3 2 6 9 2 0 6 . 3 2 7 1 7 7 6 . and Personalization, 2022, pp. 74–79. doi:h t t p s : [11] X. Zhang, H. Xie, H. Li, J. C. S. Lui, Toward building / / d o i . o r g / 1 0 . 1 1 4 5 / 3 5 1 1 0 4 7 . 3 5 3 6 4 0 8 . conversational recommender systems: A contex- [21] M. Atas, A. Felfernig, S. Polat-Erdeniz, A. Popescu, tual bandit approach, CoRR abs/1906.01219 (2019). T. N. T. Tran, M. Uta, Towards psychology-aware a r X i v : 1 9 0 6 . 0 1 2 1 9 . preference construction in recommender systems: [12] K. Zhou, W. X. Zhao, S. Bian, Y. Zhou, J.-R. Wen, Overview and research issues, Journal of Intelligent J. Yu, Improving conversational recommender sys- Information Systems (2021) 1–23. tems via knowledge graph based semantic fusion, [22] E. Lex, D. Kowald, P. Seitlinger, T. N. T. Tran, in: Proceedings of the 26th ACM SIGKDD Interna- A. Felfernig, M. Schedl, Psychology-informed rectional Conference on Knowledge Discovery & Data ommender systems, Foundations and Trends® in InMining, 2020, pp. 1006–1014. doi:1 0 . 1 1 4 5 / 3 3 9 4 4 8 6 . formation Retrieval 15 (2021) 134–242. doi:1 0 . 1 5 6 1 / 3 4 0 3 1 4 3 . 1 5 0 0 0 0 0 0 9 0 . [13] S. Li, W. Lei, Q. Wu, X. He, P. Jiang, T.-S. Chua, [23] M. Tkalcic, L. Chen, Personality and Recommender Seamlessly unifying attributes and items: Conver- Systems, Springer, Boston, MA, 2015, pp. 715–739. sational recommendation for cold-start users, ACM doi:1 0 . 1 0 0 7 / 9 7 8 - 1 - 4 8 9 9 - 7 6 3 7 - 6 _ 2 1 .

Trans. Inf. Syst. 39 (2021). doi:1 0 . 1 1 4 5 / 3 4 4 6 4 2 7 . [24] T. Z. Gizaw, H. Dong Jun, A. Oad, Solving cold-start [14] K. Zhou, Y. Zhou, W. X. Zhao, X. Wang, J.-R. Wen, problem by combining personality traits and demoTowards topic-guided conversational recommender graphic attributes in a user based recommender syssystem, in: Proceedings of the 28th International tem, International Journal of Advanced Research Conference on Computational Linguistics, Interna- in Computer Science and Software Engineering 7 tional Committee on Computational Linguistics, (2017).

Barcelona, Spain (Online), 2020, pp. 4128–4139. [25] M. Millecamp, N. N. Htun, Y. Jin, K. Verbert, Condoi:1 0 . 1 8 6 5 3 / v 1 / 2 0 2 0 . c o l i n g - m a i n . 3 6 5 . trolling spotify recommendations: Efects of per[15] I. Kostric, K. Balog, F. Radlinski, Soliciting user sonal characteristics on music recommender user preferences in conversational recommender sys- interfaces, in: Proceedings of the 26th Confertems via usage-related questions, in: 15th ACM ence on User Modeling, Adaptation and PersonConference on Recommender Systems, RecSys ’21, alization, UMAP ’18, Association for Computing 2021, pp. 724–729. Machinery, New York, NY, USA, 2018, p. 101–109. [16] L. Chen, P. Pu, Critiquing-based recommenders: doi:1 0 . 1 1 4 5 / 3 2 0 9 2 1 9 . 3 2 0 9 2 2 3 . survey and emerging trends, User Modeling and [26] J. Zhang, Anchoring efects of recommender sysUser-Adapted Interaction 22 (2012) 125–150. tems, in: Proceedings of the 5th ACM Conference [17] Y. Ma, T. Kleemann, J. Ziegler, Mixed-modality in- on Recommender Systems, RecSys ’11, Association teraction in conversational recommender systems, for Computing Machinery, New York, NY, USA, in: Interfaces and Human Decision Making for Rec- 2011, p. 375–378. doi:1 0 . 1 1 4 5 / 2 0 4 3 9 3 2 . 2 0 4 4 0 1 0 . ommender Systems 2021: Proceedings of the 8th [27] K. Hamilton, S.-I. Shih, S. Mohammed, The develJoint Workshop on Interfaces and Human Decision opment and validation of the rational and intuitive Making for Recommender Systems, 2021, pp. 21–37. decision styles scale, Journal of Personality As[18] A. Papenmeier, A. Frummet, D. Kern, “Mhm...” – sessment 98 (2016) 523–535. doi:1 0 . 1 0 8 0 / 0 0 2 2 3 8 9 1 . conversational strategies for product search assis- 2 0 1 5 . 1 1 3 2 4 2 6 . tants, in: ACM SIGIR Conference on Human Infor- [28] O. B. Büttner, A. Florack, A. S. Göritz, Shopping mation Interaction and Retrieval, CHIIR ’22, Asso- orientation as a stable consumer disposition and ciation for Computing Machinery, New York, NY, its influence on consumers’ evaluations of retailer USA, 2022, p. 36–46. doi:1 0 . 1 1 4 5 / 3 4 9 8 3 6 6 . 3 5 0 5 8 0 9 . communication, European Journal of Marketing [19] T. Kleemann, M. Wagner, B. Loepp, J. Ziegler, Mod- (2014). [29] O. B. Büttner, A. Florack, A. S. Göritz, How shop- Springer, Boston, MA, 2015, pp. 611–648. doi:1 0 . ping orientation influences the efectiveness of 1 0 0 7 / 9 7 8 - 1 - 4 8 9 9 - 7 6 3 7 - 6 _ 1 8 . monetary and nonmonetary promotions, European [32] W. Lei, X. He, Y. Miao, Q. Wu, R. Hong, M.-Y. Kan, Journal of Marketing (2015). T.-S. Chua, Estimation-action-reflection: Towards [30] W. Cai, L. Chen, Predicting user intents and sat- deep interaction between conversational and recisfaction with dialogue-based conversational rec- ommender systems, in: Proceedings of the 13th ommendations, in: Proceedings of the 28th ACM International Conference on Web Search and Data Conference on User Modeling, Adaptation and Per- Mining, 2020, pp. 304–312. doi:1 0 . 1 1 4 5 / 3 3 3 6 1 9 1 . sonalization, UMAP ’20, Association for Comput- 3 3 7 1 7 6 9 . ing Machinery, New York, NY, USA, 2020, p. 33–42. [33] E. Peer, L. Brandimarte, S. Samat, A. Acquisti, Bedoi:1 0 . 1 1 4 5 / 3 3 4 0 6 3 1 . 3 3 9 4 8 5 6 . yond the turk: Alternative platforms for crowd[31] A. Jameson, M. C. Willemsen, A. Felfernig, M. d. sourcing behavioral research, Journal of ExperimenGemmis, P. Lops, G. Semeraro, L. Chen, Hu- tal Social Psychology 70 (2017) 153–163. doi:h t t p s : man decision making and recommender sys- / / d o i . o r g / 1 0 . 1 0 1 6 / j . j e s p . 2 0 1 7 . 0 1 . 0 0 6 . tems, in: Recommender Systems Handbook,

References

[1] Y. Sun , Y. Zhang, Conversational recommender system , in: The 41st International ACM SIGIR Conference on Research & Development in Information Retrieval , SIGIR '18, Association for Computing Machinery, New York, NY, USA, 2018 , p. 235 - 244 . doi:1 0 . 1 1 4 5 / 3 2 0 9 9 7 8 . 3 2 1 0 0 0 2 .

[2] Z. Fu , Y. Xian , Y. Zhang , Y. Zhang, WSDM 2021 Tutorial on conversational recommendation systems , WSDM '21 , Association for Computing Machinery, New York, NY, USA, 2021 , p. 1134 - 1136 . doi:1 0 . 1 1 4 5 / 3 4 3 7 9 6 3 . 3 4 4 1 6 6 1 .

[3] C. Gao , W. Lei , X. He , M. de Rijke , T.-S. Chua, Advances and challenges in conversational recommender systems: A survey , AI Open 2 ( 2021 ) 100 - 126 . doi:h t t p s : / / d o i . o r g / 1 0 . 1 0 1 6 / j . a i o p e n . 2 0 2 1 . 0 6 . 0 0 2 .

[4] D. Jannach , A. Manzoor , W. Cai , L. Chen , A survey on conversational recommender systems , ACM Comput. Surv . 54 ( 2021 ). doi:1 0 . 1 1 4 5 / 3 4 5 3 1 5 4 .

[5] Z. Fu , Y. Xian , Y. Zhang , Y. Zhang, Tutorial on conversational recommendation systems , in: Fourteenth ACM Conference on Recommender Systems , RecSys '20, Association for Computing Machinery, New York, NY, USA, 2020 , p. 751 - 753 . URL: https://doi.org/10.1145/3383313. 3411548. doi:1 0 . 1 1 4 5 / 3 3 8 3 3 1 3 . 3 4 1 1 5 4 8 .

[6] B. Xiao , I. Benbasat , E-commerce product recommendation agents: Use, characteristics, and impact , MIS Q. 31 ( 2007 ) 137 - 209 .

[7] S. D. Gosling , P. J. Rentfrow , W. B. Swann , A very brief measure of the big-five personality domains , Journal of Research in Personality 37 ( 2003 ) 504 - 528 . doi:1 0 . 1 0 1 6 / S 0 0 9 2 - 6 5 6 6 ( 0 3 ) 0 0 0 4 6 - 1 .

[8] K. Hamilton , S.-I. Shih , S. Mohammed, The development and validation of the rational and intuitive decision styles scale , Journal of Personality Assessment 98 ( 2016 ) 523 - 535 . doi:1 0 . 1 0 8 0 / 0 0 2 2 3 8 9 1 . 2 0 1 5 . 1 1 3 2 4 2 6 .