Annotation-Assisted Clustering of Player Profiles in Cultural Games: A Case for Tensor Analytics in Julia
Abstract
:1. Introduction
2. Previous Work
3. Players
3.1. Bartle Taxonomy
- Explorers: Every new game is a new world and they are determined to discover it. They enjoy visiting and recording every aspect of the game world, especially Easter eggs, loot boxes, cultural references, one-time items, and even game bugs. Since cultural games are frequently built around vast—and often past—worlds abounding with items, they are literally treasure houses for them.
- Socializers: Their gaming experience essentially comes down to intricate interaction with others and exploiting every game mechanism to achieve that. Cultural games offer an excellent chance for initiating conversations about a plethora of topics and for interaction through text chats, voice messages, and writing in in-game items such as chalk boards, portraits, mirrors, and books.
- Achievers: Working tirelessly towards accomplishing game objectives and ultimately achieving them, preferably first, is why they signed up. Appearing on leaderboards adds greatly to their gaming experience. Cultural games are ideal as there is a multitude of tournaments to participate in, myriad badges and one-time items to collect, and thousands of points to accumulate.
- Killers: As their name suggests, they seek to eliminate others, preferably accomplished players. They will relate if a game recreates military campaigns such as Cæsar’s Gallic Wars (BC 58–51) or it is alternative history themed such as an open-ended American Civil War (1861–1865).
- Action vs. Interaction: The degree the actions of a player are one- or two-way.
- Environment vs. Players: The degree a player prefers the game environment or other players.
- Achievers and socializers: Achievers are highly competitive players since they often race against both the clock and other achievers of comparable or even superior skills to fulfill a set of objectives. On the contrary, socializers are very cooperative and seek harmonic and mutually beneficial coexistence with other players usually in a more relaxed style.
- Killers and explorers: Explorers aim at learning whatever is possible to be known about the game and even some more. In that sense, they are the least invasive player category as they tend to observe and not act upon the game world. On the other hand, killers do change the game world, especially if they act en masse, in numerous ways.
- Seeking different goals after gaining enough experience from the cultural game.
- Joining a team with a culture of explicit or implicit peer pressure.
- Cooperating with or competing against influential players or teams.
3.2. Player Types and Game Elements
- Points can be found in the overwhelming majority of games. Players learn to devise strategies for point maximization. Such is the case of arcade games where points are collected in large numbers.
- Badges indicate special achievements which may well be unique for every player. They can be seen approximately as the digital counterparts of real world military medals or sports cups.
- Leaderboards are highly advertised player rankings. A very high score hints at an alternative ending path. Thus, players finishing with a lower score were indirectly invited to play again.
3.3. Low Level Attributes
- The large variance of players and items involved may not always lead to numerical scales.
- Ranking ensures that attribute values remain at the same scale.
- The ranking indicates how the community is going as opposed to individual player performance.
- Ranking can be applied at various stages of the game or even for different player subsets.
3.4. High Level Attributes
3.5. First- and Higher-Order Player Profiles
- They rely on significantly more information regarding player profiles. As such, they can mine latent patterns, encoded for instance as profile similarities, player interactions, or player clusters.
- Higher-order methods tend to ignore the effect of outliers, typically expressed as unusual or missing attribute values. Properly designed methods can provide estimates for erroneous values.
- Most games create their own environment through rules or storytelling and players adapt to it. Thus, higher-order methodologies tend to reveal player types relative to the that environment.
- Gaming is mainly a social activity. Thus, although players have their own style, they may copy individual elements. For large player bases this leads to cluster formation over time.
Algorithm 1 Mapping of low-level attributes to Bartle taxonomy. |
|
Algorithm 2 Mapping of high-level attributes to Bartle taxonomy. |
|
4. Proposed Clustering Methodology
4.1. Template Simon–Ando Clustering
Algorithm 3 The power method. |
|
- For few iterations, the elements of remain close to the random starting points of .
- As the iteration progresses, the elements of move from their original positions.
- For a narrow window of iterations, the Simon–Ando phase, the elements of are clustered.
- After the Simon–Ando phase, the elements of are driven away from this clustering.
- The power method converges to and terminates.
Algorithm 4 The template Simon–Ando scheme. |
|
- Robustness: The harmonic mean in sharp contrast to the geometric mean is immune to erroneous values close to zero or to outliers in general.
- Reliability: For stochastic input, even for a relatively few observations and for a wide array of distributions, the harmonic mean converges to its true value.
4.2. Tensor-Based Clustering
- The two cluster schemes for and are initialized with random entries.
- If user annotations are used, then is multiplied by once during initialization.
- Tensor multiplies matrix , essentially filtering and through and , respectively.
- At the next step, the two columns of matrix are swapped through matrix .
5. Results
5.1. Setup
- First vs. higher order: These tests examine the clustering quality achieved by the first-order mappings of Algorithms 1 and 2 compared to that of the higher-order iterative clustering methods. Recall that the latter aggregate local ground truth to reveal global properties.
- Tensor vs. matrix: From the iteration template of Algorithm 4, matrix- and tensor-based clustering schemes are derived as outlined in Table 7. The objective is to determine whether switching to the latter can offer an advantage concerning player clustering ignoring annotations.
- Effect of annotations: These experiments aim at evaluating the effect of user annotations. To this end, the methods relying on user annotations to obtain weights for the high-level attributes are compared against their counterparts without these weights.
5.2. Dataset Synopsis
- Annotator: The user creating the annotation. This field is independent of the player(s) involved in the activity. As such, it was ignored as it did not contribute information to the experiments.
- Timestamp: Automatically generated date and time of the annotation in ISO 8601 format. This field was also ignored as it was not relevant to the analysis conducted here.
- Category: It is one of the possible categories: Interaction of a player with a player or with an NPC, presence of a player in the alternative timelines, and interaction with players in a tournament.
- Subject: The player who does or initiates an action, as described in the respective field. To keep annotations simple, even in multiplayer events only elementary actions were recorded.
- Object: The player or NPC who is the target of the action, where applicable. It has the same format with the previous field but its semantics are much different from an analysis perspective.
- Action: Although there are many actions, here stand out the cooperation and the competition in tournaments and the participation to timelines. Everything else is listed as generic interaction.
5.3. Number of Iterations and Floating Point Operations
- The matrix based methods systematically yield a higher number of iterations. Thus, their convergence to the same level is slower compared to the tensor based ones.
- The annotation based methods achieve systematically lower number of iterations from their counterparts. This is a clear indication that they contribute to the overall clustering quality.
- The combination of tensor representation with the user annotations resulted in the lowest number of iterations. Therefore, they contribute individually to mining knowledge from the dataset.
- The tensor based methods achieve a somewhat lower number of flops although they contain more expensive operations of linear algebra. This can be attributed to the lower number of iterations.
- The cost for incorporating annotations is negligible, as can be seen from the entries for flops. Thus, it pays off to have them in the scheme as part of the mining strategy.
5.4. Cluster Distance
- The average inter-cluster distance of Equation (16)
- The maximum inter-cluster distance of Equation (17)
- The average intra-cluster distance of Equation (19)
- The tensor based methods consistently result in better separated clusters both in the average distance case and in the maximum distance as indicated respectively by the high values of and . This means that bounds between clusters contains fewer data points and are more clear.
- The tensor based methods yield more compact clusters compared to the matrix based ones, as indicated by the low values of . This complements the findings for and , as more distant clusters “push” the same number of data points to smaller regions, resulting in higher density.
- Both the above hold even more when the annotation-based methods are compared against their counterparts. This is a clear indication that the inclusion of user annotations improves the overall clustering process. Combined with the tensor representation, this is even more enhanced.
5.5. Player Type Distribution
- First-order distributions: It is the player type distribution as obtained by Algorithms 1 and 2. Therefore, the mapping from the player profile to the Bartle taxonomy is based on the former.
- Higher-order distributions: Once a clustering scheme is complete, clusters are formed, profiles are mapped as before, and then each player receives the majority type of the respective cluster.
- All methods yield approximately the same percentage for achievers. This also almost holds for socializers. This is an indication these player categories may have distinct behavior which can be almost directly translated to both low- and high-level attributes.
- The first-order distributions and the matrix method give a very high number for killers which is inconsistent with the very low number obtained from the remaining methods. A possible explanation is they tend to treat as killers every profile not fulfilling the criteria for the other types.
- The tensor-based methods yield almost identical distributions. This may be an indication that despite the different starting points they both eventually converge to the same distribution exploiting higher order patterns with annotations accelerating this convergence.
- The above is also true but to a lesser extent for the results from the comb and the comb-a iterative schemes. This can be attributed to the fact that annotations help the clustering process but do not suffice by themselves to uncover all the patterns in the processed dataset.
5.6. Discussion
- Humans can almost immediately understand both the complex semantics inherent in player actions and the possible ultimate objectives of other players, especially in the context of the game.
- Moreover, dedicated or even casual players can draw on considerable information from their respective gaming experience in order to interpret the actions of other players.
- Annotations, as explained above, are driven to the data mining algorithms for interpreting the actions of the players. In turn, this leads to a better understanding of the player base.
- Annotations are also analyzed in terms of the players who gave them. This gives insight into the segment of players who are willing to improve the game, participating thus in a deeper level.
- The value of the available cultural objects for the player base is estimated through analytics based on the annotations. This is an important cultural preservation function.
6. Recommendations
- Table 2 will serve as a guide for the relationship between game elements and the basic emotions they elicit across player types. However, this is only a statistical approach.
- The last column of Table 13, namely the results of clustering with the tensor-a methodology, will be considered as the true player base distribution.
7. Conclusions and Future Work
Author Contributions
Funding
Conflicts of Interest
References
- Squire, K. Cultural framing of computer/video games. Game Stud. 2002, 2, 1–13. [Google Scholar]
- Mortara, M.; Catalano, C.E.; Bellotti, F.; Fiucci, G.; Houry-Panchetti, M.; Petridis, P. Learning cultural heritage by serious games. J. Cult. Herit. 2014, 15, 318–325. [Google Scholar] [CrossRef] [Green Version]
- ANTIKLEIA Greek Web Site. Available online: https://www.antikleia.gr (accessed on 20 November 2020).
- Europeana Web Site. Available online: https://www.europeana.eu/en (accessed on 20 November 2020).
- ANTIKLEIA Web Site. Available online: http://antikleia.website/ (accessed on 20 November 2020).
- Lumsden, J.; Edwards, E.A.; Lawrence, N.S.; Coyle, D.; Munafò, M.R. Gamification of cognitive assessment and cognitive training: A systematic review of applications and efficacy. JMIR Ser. Games 2016, 4, e11. [Google Scholar] [CrossRef] [PubMed] [Green Version]
- Lister, M. Gamification: The effect on student motivation and performance at the post-secondary level. Issues Trends Educ. Technol. 2015, 3, 112–120. [Google Scholar] [CrossRef]
- Streukens, S.; van Riel, A.; Novikova, D.; Leroi-Werelds, S. Boosting customer engagement through gamification: A customer engagement marketing approach. In Handbook of Research on Customer Engagement; Edward Elgar Publishing: London, UK, 2019. [Google Scholar]
- Landers, R.N.; Bauer, K.N.; Callan, R.C. Gamification of task performance with leaderboards: A goal setting experiment. Comput. Hum. Behav. 2017, 71, 508–515. [Google Scholar] [CrossRef]
- Huang, B.; Hew, K.F. Do points, badges and leaderboard increase learning and activity: A quasi-experiment on the effects of gamification. In Proceedings of the 23rd International Conference on Computers in Education, Ishikawa, Japan, 30 November–4 December 2015; pp. 275–280. [Google Scholar]
- Seaborn, K.; Fels, D.I. Gamification in theory and action: A survey. Int. J. Hum.-Comput. Stud. 2015, 74, 14–31. [Google Scholar] [CrossRef]
- Triantoro, T.; Gopal, R.; Benbunan-Fich, R.; Lang, G. Would you like to play? A comparison of a gamified survey with a traditional online survey method. Int. J. Inf. Manag. 2019, 49, 242–252. [Google Scholar] [CrossRef]
- Menéndez, H.D.; Vindel, R.; Camacho, D. Combining time series and clustering to extract gamer profile evolution. In International Conference on Computational Collective Intelligence; Springer: Heidelberg, Germany, 2014; pp. 262–271. [Google Scholar]
- Jia, Y.; Liu, Y.; Yu, X.; Voida, S. Designing leaderboards for gamification: Perceived differences based on user ranking, application domain, and personality traits. In Proceedings of the Conference on Human Factors in Computing Systems, Denver, CO, USA, 6–11 May 2017; pp. 1949–1960. [Google Scholar]
- Codish, D.; Ravid, G. Detecting playfulness in educational gamification through behavior patterns. IBM J. Res. Dev. 2015, 59, 1–6. [Google Scholar] [CrossRef] [Green Version]
- Conejo, F. Loyalty 3.0: How to revolutionize customer and employee engagement with big data and gamification. J. Consum. Mark. 2014, 31, 86–87. [Google Scholar]
- Kim, B. The Popularity of Gamification in the Mobile and Social Era. Libr. Technol. Rep. 2015, 51, 5–9. [Google Scholar]
- Kyriazidou, I.; Drakopoulos, G.; Kanavos, A.; Makris, C.; Mylonas, P. Towards Predicting Mentions to Verified Twitter Accounts: Building Prediction Models over MongoDB with keras. In WEBIST; ScitePress: Setubal, Portugal, 2019; pp. 25–33. [Google Scholar]
- Tekofsky, S.; Van Den Herik, J.; Spronck, P.; Plaat, A. PsyOps: Personality assessment through gaming behavior. In Proceedings of the International Conference on the Foundations of Digital Games, SASDG, Crete, Greece, 14–17 May 2013. [Google Scholar]
- Yang, W.; Rifqi, M.; Marsala, C.; Pinna, A. Physiological-based emotion detection and recognition in a video game context. In Proceedings of the IJCNN, Rio de Janeiro, Brazil, 8–13 July 2018; pp. 1–8. [Google Scholar]
- Drakopoulos, G.; Pikrammenos, G.; Spyrou, E.D.; Perantonis, S.J. Emotion Recognition from Speech: A Survey. In Proceedings of the 2014 International Conference on Circuits, Systems, Communication and Information Technology Applications (CSCITA), Mumbai, India, 4–5 April 2019; pp. 432–439. [Google Scholar]
- De Lathauwer, L. Signal Processing Based on Multilinear Algebra. Ph.D. Thesis, KU Leuven, Leuven, Belgium, 1997. [Google Scholar]
- De Lathauwer, L.; De Moor, B. From matrix to tensor: Multilinear algebra and signal processing. In Institute of Mathematics and Its Applications Conference Series; Oxford University Press: Oxford, MA, USA, 1998; Volume 67, pp. 1–16. [Google Scholar]
- Papalexakis, E.E.; Pelechrinis, K.; Faloutsos, C. Spotting misbehaviors in location-based social networks using tensors. In Proceedings of the WWW 14: 23rd International World Wide Web Conference, Seoul, Korea, 7–11 April 2014; pp. 551–552. [Google Scholar] [CrossRef]
- Papalexakis, E.E.; Faloutsos, C. Fast efficient and scalable core consistency diagnostic for the PARAFAC decomposition for big sparse tensors. In Proceedings of the ICASSP 2015, Brisbane, Australia, 19–24 April 2015; pp. 5441–5445. [Google Scholar]
- Alexopoulos, A.; Drakopoulos, G.; Kanavos, A.; Mylonas, P.; Vonitsanos, G. Two-Step Classification with SVD Preprocessing of Distributed Massive Datasets in Apache Spark. Algorithms 2020, 13, 71. [Google Scholar] [CrossRef] [Green Version]
- Bao, Y.T.; Chien, J.T. Tensor classification network. In MLSP; IEEE: Piscataway, NJ, USA, 2015; pp. 1–6. [Google Scholar]
- Drakopoulos, G.; Mylonas, P. Evaluating graph resilience with tensor stack networks: A keras implementation. Neural Comput. Appl. 2020, 32, 4161–4176. [Google Scholar] [CrossRef]
- Benson, A.R.; Gleich, D.F.; Leskovec, J. Tensor spectral clustering for partitioning higher-order network structures. In ICDM; SIAM: New Delhi, India, 2015; pp. 118–126. [Google Scholar]
- Yu, D.; Deng, L.; Seide, F. The deep tensor neural network with applications to large vocabulary speech recognition. IEEE Trans. Audio Speech Lang. Process. 2012, 21, 388–396. [Google Scholar] [CrossRef]
- Yu, D.; Deng, L.; Seide, F. Large vocabulary speech recognition using deep tensor neural networks. In Proceedings of the INTERSPEECH 2012 ISCA’s 13th Annual Conference, Portland, OR, USA, 9–13 September 2012. [Google Scholar]
- Ma, J.; Liu, X.Y.; Shou, Z.; Yuan, X. Deep tensor admm-net for snapshot compressive imaging. In Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision (ICCV), Seoul, Korea, 27 October–2 November 2019; pp. 10223–10232. [Google Scholar]
- Drakopoulos, G.; Stathopoulou, F.; Kanavos, A.; Paraskevas, M.; Tzimas, G.; Mylonas, P.; Iliadis, L. A genetic algorithm for spatiosocial tensor clustering: Exploiting TensorFlow potential. Evol. Syst. 2019. [Google Scholar] [CrossRef]
- Abadi, M.; Barham, P.; Chen, J.; Chen, Z.; Davis, A.; Dean, J.; Devin, M.; Ghemawat, S.; Irving, G.; Isard, M.; et al. TensorFlow: A system for large-scale machine learning. In OSDI’16; USENIX Association: Berkeley, CA, USA, 2016; pp. 265–283. [Google Scholar]
- Abadi, M. TensorFlow: Learning functions at scale. In SIGPLAN International Conference on Functional Programming; ACM: New York, NY, USA, 2016; pp. 1–8. [Google Scholar]
- Palzer, D.; Hutchinson, B. The tensor deep stacking network toolkit. In IJCNN; IEEE: Piscataway, NJ, USA, 2015; pp. 1–5. [Google Scholar]
- Drakopoulos, G.; Mylonas, P.; Sioutas, S. A Case of Adaptive Nonlinear System Identification with Third Order Tensors in TensorFlow. In INISTA; IEEE: Piscataway, NJ, USA, 2019; pp. 1–6. [Google Scholar] [CrossRef]
- imdb. Ready Player One. Available online: imdb.com/title/tt16777720 (accessed on 28 September 2020).
- Star Citizen. Wing Commander I 25th Anniversary Gameplay Video. Available online: https://www.youtube.com/watch?v=ADrl5uWckJw (accessed on 28 September 2020).
- imdb. Wing Commander. Available online: imdb.com/title/tt0245563 (accessed on 28 September 2020).
- WC CIC. Wing Commander. Available online: www.wcnews.com (accessed on 28 September 2020).
- Mori, M.; MacDorman, K.F.; Kageki, N. The uncanny valley [from the field]. IEEE Robot. Autom. Mag. 2012, 19, 98–100. [Google Scholar] [CrossRef]
- Bryan, J.I. Japanese Story-Telling. Lotus Mag. 1914, 5, 407–412. [Google Scholar]
- Chou, Y.k. Actionable Gamification: Beyond Points, Badges, and Leaderboards; Packt Publishing Ltd.: Birmingham, UK, 2019. [Google Scholar]
- Levin, S.A. The architecture of robustness. In Global Challenges, Governance, and Complexity; Edward Elgar Publishing: Cheltenham, UK, 2019. [Google Scholar]
- Vallet, D.; Fernandez, M.; Castells, P.; Mylonas, P.; Avrithis, Y. A contextual personalization approach based on ontological knowledge. Contexts Ontol. Theory Pract. Appl. 2006, 2006, 35. [Google Scholar]
- Diplaris, S.; Sonnenbichler, A.; Kaczanowski, T.; Mylonas, P.; Scherp, A.; Janik, M.; Papadopoulos, S.; Ovelgoenne, M.; Kompatsiaris, Y. Emerging, collective intelligence for personal, organisational and social use. In Next Generation Data Technologies for Collective Computational Intelligence; Springer: Berlin, Germany, 2011; pp. 527–573. [Google Scholar]
- Hartfiel, D. Proof of the Simon-Ando theorem. Proc. Am. Math. Soc. 1996, 124, 67–74. [Google Scholar] [CrossRef] [Green Version]
- Yang, J.; Fan, J.; Wei, Z.; Li, G.; Liu, T.; Du, X. Cost-effective data annotation using game-based crowdsourcing. PVLDB 2018, 12, 57–70. [Google Scholar] [CrossRef] [Green Version]
- Yang, J.; Fan, J.; Wei, Z.; Li, G.; Liu, T.; Du, X. A game-based framework for crowdsourced data labeling. VLDB J. 2020, 29, 1311–1336. [Google Scholar] [CrossRef]
- Seneviratne, L.; Izquierdo, E. An interactive framework for image annotation through gaming. In Proceedings of the International Conference on Multimedia Information Retrieval, Philadelphia, PA, USA, 29–31 March 2010; pp. 517–526. [Google Scholar]
- Yannakakis, G.N.; Paiva, A. Emotion in games. In Handbook on Affective Computing; Springer: Berlin/Heidelberg, Germany, 2014; pp. 459–471. [Google Scholar]
- Liu, T.; Yang, J.; Fan, J.; Wei, Z.; Li, G.; Du, X. CrowdGame: A Game-Based Crowdsourcing System for Cost-Effective Data Labeling. In Proceedings of the International Conference on Management of Data, Amsterdam, The Netherlands, 30 June–5 July 2019; pp. 1957–1960. [Google Scholar]
- Voutos, Y.; Drakopoulos, G.; Mylonas, P. Metadata-enriched Discovery of Aspect Similarities Between Cultural Objects. In SMAP; IEEE: Piscataway, NJ, USA, 2020. [Google Scholar] [CrossRef]
- Drakopoulos, G.; Voutos, Y.; Mylonas, P. Recent Advances On Ontology Similarity Metrics: A Survey. In SEEDA-CECNSM; IEEE: Piscataway, NJ, USA, 2020. [Google Scholar] [CrossRef]
Symbol | Meaning | Introduced in |
---|---|---|
Definition or equality by definition | Equation (1) | |
Set with elements | Equation (1) | |
Tuple with elements | Equation (16) | |
Cardinality of set or tuple S | Equation (18) | |
Tensor multiplication along dimension k | Equation (11) | |
identity matrix | Equation (8) | |
column reversal matrix | Equation (14) |
Element | Explorers | Socializers | Achievers | Killers |
---|---|---|---|---|
Points | Neutral | Neutral | Joy | Neutral |
Badges | Anticipation | Neutral | Anticipation | Joy |
Leaderboards | Neutral | Anticipation | Joy | Joy |
One-time items | Surprise | Neutral | Joy | Joy |
Easter eggs | Joy | Neutral | Joy | Neutral |
Loot boxes | Joy | Joy | Joy | Neutral |
Secret rooms | Anticipation | Neutral | Joy | Neutral |
Writable objects | Neutral | Anticipation | Neutral | Neutral |
Cultural references | Joy | Anticipation | Neutral | Neutral |
Interaction with players | Joy | Trust | Neutral | Anticipation |
Interaction with NPCs | Neutral | Anticipation | Neutral | Anticipation |
In-game tournaments | Surprise | Neutral | Surprise | Neutral |
Cooperation in tournaments | Neutral | Joy | Neutral | Anger |
Competition in tournaments | Neutral | Anger | Neutral | Joy |
Alternative timelines | Anticipation | Joy | Anticipation | Anticipation |
Crossovers | Joy | Neutral | Neutral | Neutral |
Linear storytelling | Neutral | Neutral | Neutral | Joy |
In media res storytelling | Joy | Neutral | Neutral | Anticipation |
Open world | Joy | Joy | Anticipation | Joy |
Open universe | Anticipation | Anticipation | Joy | Joy |
Connection to physical world | Anticipation | Joy | Neutral | Neutral |
Element | Mnemonic | Quantile Meaning | Element | Mnemonic | Quantile Meaning |
---|---|---|---|---|---|
points | Points accumulated | eggs | Easter eggs found | ||
badges | Badges collected | loot | Loot boxes found | ||
board | Leaderboard position | rooms | Secret rooms found | ||
items | One-time items collected | writeable | Writable objects used |
Numerical | 1 | ||||
Symbolic | Weak | Low | Medium | High | Strong |
Element | Mnemonic | Quantile Meaning | Element | Mnemonic | Quantile Meaning |
---|---|---|---|---|---|
players | Interaction with players | competition | Tournament competition | ||
npcs | Interaction with NPCs | timelines | Participation to timelines | ||
tours | Tournament participation | crossovers | Participation to crossovers | ||
cooperation | Tournament cooperation | world | Fraction of world explored |
Annotation | Symbol | Category | Meaning |
---|---|---|---|
Player | Interaction | A player has interacted with another (not in tournament) | |
NPC | Interaction | A player has interacted with an NPC (not in tournament) | |
Timelines | Game world | A player participates to an in-game alternative timeline | |
Cooperation | Tournament activity | A player has cooperated with another player | |
Competition | Tournament activity | A player has competed against another player |
Method | Kernel | Explicit | Attributes | Annotations |
---|---|---|---|---|
matrix | Matrix | Yes | Low | No |
comb | Matrix | Yes | Low+High | No |
comb-a | Matrix | Yes | Low+High | Yes |
tensor | Tensor | No | Low+High | No |
tensor-a | Tensor | No | Low+High | Yes |
Parameter | Value | Parameter | Value |
---|---|---|---|
Number of attributes | 8 | Attribute groups | 2 (low and high) |
Maximum vector size | 1 MB | Processor | Intel Core i5 3210M @ 1.6 GHz |
Maximum matrix size | 8 MB | Main memory size | 16 GB |
Maximum tensor size | 16 MB | L1/L2/L3 cache size | 1/3/4 MB |
Raw dataset rows | 175 K | Processed dataset rows | 64 K |
Number of annotators | 8617 | Annotation options | 11 |
Number of players | 1024 | Termination threshold | |
Number of runs | 1000 | Maximum number of iterations | 1024 |
Player | NPC | Timelines | Cooperation | Competition |
---|---|---|---|---|
Matrix | Comb | Comb-a | Tensor | Tensor-a | |
---|---|---|---|---|---|
mean | |||||
var |
Matrix | Comb | Comb-a | Tensor | Tensor-a | |
---|---|---|---|---|---|
mean | |||||
var |
Matrix | Comb | Comb-a | Tensor | Tensor-a | |
---|---|---|---|---|---|
1 | |||||
1 | |||||
1 |
Algo. 1 | Algo. 2 | Matrix | Comb | Comb-a | Tensor | Tensor-a | |
---|---|---|---|---|---|---|---|
Achievers | |||||||
Explorers | |||||||
Socializers | |||||||
Killers |
Element | Score | Element | Score | Element | Score | Element | Score |
---|---|---|---|---|---|---|---|
Points | Eggs | Players | Competition | ||||
Badges | Boxes | NPCs | Alternative | 1 | |||
Leaderboards | Rooms | Tournaments | Crossovers | ||||
One-time | Writable | Cooperation | World | 1 |
Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. |
© 2020 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).
Share and Cite
Drakopoulos, G.; Voutos, Y.; Mylonas, P. Annotation-Assisted Clustering of Player Profiles in Cultural Games: A Case for Tensor Analytics in Julia. Big Data Cogn. Comput. 2020, 4, 39. https://doi.org/10.3390/bdcc4040039
Drakopoulos G, Voutos Y, Mylonas P. Annotation-Assisted Clustering of Player Profiles in Cultural Games: A Case for Tensor Analytics in Julia. Big Data and Cognitive Computing. 2020; 4(4):39. https://doi.org/10.3390/bdcc4040039
Chicago/Turabian StyleDrakopoulos, Georgios, Yorghos Voutos, and Phivos Mylonas. 2020. "Annotation-Assisted Clustering of Player Profiles in Cultural Games: A Case for Tensor Analytics in Julia" Big Data and Cognitive Computing 4, no. 4: 39. https://doi.org/10.3390/bdcc4040039